linux-pikaos-template/patches/0002-eevdf.patch

From 0365d5da967f712e2210bc34b0bd3c17aa752ad3 Mon Sep 17 00:00:00 2001
From: Peter Jung <admin@ptr1337.dev>
Date: Mon, 17 Apr 2023 18:43:10 +0200
Subject: [PATCH] EEVDF

Signed-off-by: Peter Jung <admin@ptr1337.dev>
---
 Documentation/admin-guide/cgroup-v2.rst |   10 +
 include/linux/rbtree_augmented.h        |   26 +
 include/linux/sched.h                   |    9 +-
 include/uapi/linux/sched.h              |    4 +-
 include/uapi/linux/sched/types.h        |   19 +
 init/init_task.c                        |    3 +-
 kernel/sched/core.c                     |   67 +-
 kernel/sched/debug.c                    |   50 +-
 kernel/sched/fair.c                     | 1230 +++++++++++------------
 kernel/sched/features.h                 |   28 +-
 kernel/sched/sched.h                    |   23 +-
 tools/include/uapi/linux/sched.h        |    4 +-
 12 files changed, 756 insertions(+), 717 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index f67c0829350b..a39dfda3d032 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1121,6 +1121,16 @@ All time durations are in microseconds.
         values similar to the sched_setattr(2). This maximum utilization
         value is used to clamp the task specific maximum utilization clamp.
 
+  cpu.latency.nice
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	The nice value is in the range [-20, 19].
+
+	This interface file allows reading and setting latency using the
+	same values used by sched_setattr(2). The latency_nice of a group is
+	used to limit the impact of the latency_nice of a task outside the
+	group.
 
 
 Memory
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index d1c53e9d8c75..a78e692a9ff5 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -60,6 +60,32 @@ rb_insert_augmented_cached(struct rb_node *node,
 	rb_insert_augmented(node, &root->rb_root, augment);
 }
 
+static __always_inline struct rb_node *
+rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree,
+			bool (*less)(struct rb_node *, const struct rb_node *),
+			const struct rb_augment_callbacks *augment)
+{
+	struct rb_node **link = &tree->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	bool leftmost = true;
+
+	while (*link) {
+		parent = *link;
+		if (less(node, parent)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = false;
+		}
+	}
+
+	rb_link_node(node, parent, link);
+	augment->propagate(parent, NULL); /* suboptimal */
+	rb_insert_augmented_cached(node, tree, leftmost, augment);
+
+	return leftmost ? node : NULL;
+}
+
 /*
  * Template for declaring augmented rbtree callbacks (generic case)
  *
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d398b337b0d..6a719374f688 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,6 +548,9 @@ struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
 	struct rb_node			run_node;
+	u64				deadline;
+	u64				min_deadline;
+
 	struct list_head		group_node;
 	unsigned int			on_rq;
 
@@ -555,11 +558,10 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				vruntime;
 	u64				prev_sum_exec_runtime;
+	s64				vlag;
+	u64				slice;
 
 	u64				nr_migrations;
-	u64				prev_sleep_sum_runtime;
-	/* average duration of a task */
-	u64				dur_avg;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	int				depth;
@@ -787,6 +789,7 @@ struct task_struct {
 	int				static_prio;
 	int				normal_prio;
 	unsigned int			rt_priority;
+	int				latency_prio;
 
 	struct sched_entity		se;
 	struct sched_rt_entity		rt;
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..b2e932c25be6 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ struct clone_args {
 #define SCHED_FLAG_KEEP_PARAMS		0x10
 #define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
 #define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+#define SCHED_FLAG_LATENCY_NICE		0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
 			 SCHED_FLAG_RECLAIM		| \
 			 SCHED_FLAG_DL_OVERRUN		| \
 			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
+			 SCHED_FLAG_UTIL_CLAMP		| \
+			 SCHED_FLAG_LATENCY_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h
index f2c4589d4dbf..db1e8199e8c8 100644
--- a/include/uapi/linux/sched/types.h
+++ b/include/uapi/linux/sched/types.h
@@ -10,6 +10,7 @@ struct sched_param {
 
 #define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
 #define SCHED_ATTR_SIZE_VER1	56	/* add: util_{min,max} */
+#define SCHED_ATTR_SIZE_VER2	60	/* add: latency_nice */
 
 /*
  * Extended scheduling parameters data structure.
@@ -98,6 +99,22 @@ struct sched_param {
  * scheduled on a CPU with no more capacity than the specified value.
  *
  * A task utilization boundary can be reset by setting the attribute to -1.
+ *
+ * Latency Tolerance Attributes
+ * ===========================
+ *
+ * A subset of sched_attr attributes allows to specify the relative latency
+ * requirements of a task with respect to the other tasks running/queued in the
+ * system.
+ *
+ * @ sched_latency_nice	task's latency_nice value
+ *
+ * The latency_nice of a task can have any value in a range of
+ * [MIN_LATENCY_NICE..MAX_LATENCY_NICE].
+ *
+ * A task with latency_nice with the value of LATENCY_NICE_MIN can be
+ * taken for a task requiring a lower latency as opposed to the task with
+ * higher latency_nice.
  */
 struct sched_attr {
 	__u32 size;
@@ -120,6 +137,8 @@ struct sched_attr {
 	__u32 sched_util_min;
 	__u32 sched_util_max;
 
+	/* latency requirement hints */
+	__s32 sched_latency_nice;
 };
 
 #endif /* _UAPI_LINUX_SCHED_TYPES_H */
diff --git a/init/init_task.c b/init/init_task.c
index ff6c4b9bfe6b..511cbcf3510d 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -78,6 +78,7 @@ struct task_struct init_task
 	.prio		= MAX_PRIO - 20,
 	.static_prio	= MAX_PRIO - 20,
 	.normal_prio	= MAX_PRIO - 20,
+	.latency_prio	= DEFAULT_PRIO,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
@@ -89,7 +90,7 @@ struct task_struct init_task
 		.fn = do_no_restart_syscall,
 	},
 	.se		= {
-		.group_node 	= LIST_HEAD_INIT(init_task.se.group_node),
+		.group_node	= LIST_HEAD_INIT(init_task.se.group_node),
 	},
 	.rt		= {
 		.run_list	= LIST_HEAD_INIT(init_task.rt.run_list),
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 17bb9637f314..fbc08605b068 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1285,6 +1285,12 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	}
 }
 
+static inline void set_latency_prio(struct task_struct *p, int prio)
+{
+	p->latency_prio = prio;
+	set_latency_fair(&p->se, prio - MAX_RT_PRIO);
+}
+
 #ifdef CONFIG_UCLAMP_TASK
 /*
  * Serializes updates of utilization clamp values
@@ -4434,10 +4440,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
-	p->se.dur_avg			= 0;
-	p->se.prev_sleep_sum_runtime	= 0;
+	p->se.vlag			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+	set_latency_prio(p, p->latency_prio);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
 #endif
@@ -4688,6 +4695,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
+		set_latency_prio(p, NICE_TO_PRIO(0));
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -7433,7 +7441,7 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 #define SETPARAM_POLICY	-1
 
 static void __setscheduler_params(struct task_struct *p,
-		const struct sched_attr *attr)
+				  const struct sched_attr *attr)
 {
 	int policy = attr->sched_policy;
 
@@ -7457,6 +7465,13 @@ static void __setscheduler_params(struct task_struct *p,
 	set_load_weight(p, true);
 }
 
+static void __setscheduler_latency(struct task_struct *p,
+				   const struct sched_attr *attr)
+{
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE)
+		set_latency_prio(p, NICE_TO_PRIO(attr->sched_latency_nice));
+}
+
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -7597,6 +7612,13 @@ static int __sched_setscheduler(struct task_struct *p,
 			return retval;
 	}
 
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		if (attr->sched_latency_nice > MAX_NICE)
+			return -EINVAL;
+		if (attr->sched_latency_nice < MIN_NICE)
+			return -EINVAL;
+	}
+
 	if (pi)
 		cpuset_read_lock();
 
@@ -7631,6 +7653,9 @@ static int __sched_setscheduler(struct task_struct *p,
 			goto change;
 		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
 			goto change;
+		if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE &&
+		    attr->sched_latency_nice != PRIO_TO_NICE(p->latency_prio))
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		retval = 0;
@@ -7719,6 +7744,7 @@ static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_params(p, attr);
 		__setscheduler_prio(p, newprio);
 	}
+	__setscheduler_latency(p, attr);
 	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
@@ -7929,6 +7955,9 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	    size < SCHED_ATTR_SIZE_VER1)
 		return -EINVAL;
 
+	if ((attr->sched_flags & SCHED_FLAG_LATENCY_NICE) &&
+	    size < SCHED_ATTR_SIZE_VER2)
+		return -EINVAL;
 	/*
 	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
@@ -8166,6 +8195,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	get_params(p, &kattr);
 	kattr.sched_flags &= SCHED_FLAG_ALL;
 
+	kattr.sched_latency_nice = PRIO_TO_NICE(p->latency_prio);
+
 #ifdef CONFIG_UCLAMP_TASK
 	/*
 	 * This could race with another potential updater, but this is fine
@@ -11038,6 +11069,25 @@ static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
 {
 	return sched_group_set_idle(css_tg(css), idle);
 }
+
+static s64 cpu_latency_nice_read_s64(struct cgroup_subsys_state *css,
+				    struct cftype *cft)
+{
+	return PRIO_TO_NICE(css_tg(css)->latency_prio);
+}
+
+static int cpu_latency_nice_write_s64(struct cgroup_subsys_state *css,
+				     struct cftype *cft, s64 nice)
+{
+	int prio;
+
+	if (nice < MIN_NICE || nice > MAX_NICE)
+		return -ERANGE;
+
+	prio = NICE_TO_PRIO(nice);
+
+	return sched_group_set_latency(css_tg(css), prio);
+}
 #endif
 
 static struct cftype cpu_legacy_files[] = {
@@ -11052,6 +11102,11 @@ static struct cftype cpu_legacy_files[] = {
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency.nice",
+		.read_s64 = cpu_latency_nice_read_s64,
+		.write_s64 = cpu_latency_nice_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
@@ -11269,6 +11324,12 @@ static struct cftype cpu_files[] = {
 		.read_s64 = cpu_idle_read_s64,
 		.write_s64 = cpu_idle_write_s64,
 	},
+	{
+		.name = "latency.nice",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_latency_nice_read_s64,
+		.write_s64 = cpu_latency_nice_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8d64fba16cfe..e0d10ac21016 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -308,10 +308,7 @@ static __init int sched_init_debug(void)
 	debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
 #endif
 
-	debugfs_create_u32("latency_ns", 0644, debugfs_sched, &sysctl_sched_latency);
-	debugfs_create_u32("min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_min_granularity);
-	debugfs_create_u32("idle_min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_idle_min_granularity);
-	debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity);
+	debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
 
 	debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
 	debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
@@ -535,9 +532,13 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	else
 		SEQ_printf(m, " %c", task_state_to_char(p));
 
-	SEQ_printf(m, " %15s %5d %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, "%15s %5d %9Ld.%06ld %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
 		p->comm, task_pid_nr(p),
 		SPLIT_NS(p->se.vruntime),
+		entity_eligible(cfs_rq_of(&p->se), &p->se) ? 'E' : 'N',
+		SPLIT_NS(p->se.deadline),
+		SPLIT_NS(p->se.slice),
+		SPLIT_NS(p->se.sum_exec_runtime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
@@ -580,10 +581,9 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
-	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
-		spread, rq0_min_vruntime, spread0;
+	s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
+	struct sched_entity *last, *first;
 	struct rq *rq = cpu_rq(cpu);
-	struct sched_entity *last;
 	unsigned long flags;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -597,26 +597,25 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
-	if (rb_first_cached(&cfs_rq->tasks_timeline))
-		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
+	first = __pick_first_entity(cfs_rq);
+	if (first)
+		left_vruntime = first->vruntime;
 	last = __pick_last_entity(cfs_rq);
 	if (last)
-		max_vruntime = last->vruntime;
+		right_vruntime = last->vruntime;
 	min_vruntime = cfs_rq->min_vruntime;
-	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
 	raw_spin_rq_unlock_irqrestore(rq, flags);
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
-			SPLIT_NS(MIN_vruntime));
+
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "left_vruntime",
+			SPLIT_NS(left_vruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
 			SPLIT_NS(min_vruntime));
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "max_vruntime",
-			SPLIT_NS(max_vruntime));
-	spread = max_vruntime - MIN_vruntime;
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread",
-			SPLIT_NS(spread));
-	spread0 = min_vruntime - rq0_min_vruntime;
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
-			SPLIT_NS(spread0));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "avg_vruntime",
+			SPLIT_NS(avg_vruntime(cfs_rq)));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "right_vruntime",
+			SPLIT_NS(right_vruntime));
+	spread = right_vruntime - left_vruntime;
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
@@ -817,10 +816,7 @@ static void sched_debug_header(struct seq_file *m)
 	SEQ_printf(m, "  .%-40s: %Ld\n", #x, (long long)(x))
 #define PN(x) \
 	SEQ_printf(m, "  .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
-	PN(sysctl_sched_latency);
-	PN(sysctl_sched_min_granularity);
-	PN(sysctl_sched_idle_min_granularity);
-	PN(sysctl_sched_wakeup_granularity);
+	PN(sysctl_sched_base_slice);
 	P(sysctl_sched_child_runs_first);
 	P(sysctl_sched_features);
 #undef PN
@@ -1024,7 +1020,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	__PS("nr_involuntary_switches", p->nivcsw);
 
 	P(se.load.weight);
-	P(se.dur_avg);
 #ifdef CONFIG_SMP
 	P(se.avg.load_sum);
 	P(se.avg.runnable_sum);
@@ -1044,6 +1039,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 #endif
 	P(policy);
 	P(prio);
+	P(latency_prio);
 	if (task_has_dl_policy(p)) {
 		P(dl.runtime);
 		P(dl.deadline);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0f92281fbed9..917f0cc106b6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -47,6 +47,7 @@
 #include <linux/psi.h>
 #include <linux/ratelimit.h>
 #include <linux/task_work.h>
+#include <linux/rbtree_augmented.h>
 
 #include <asm/switch_to.h>
 
@@ -56,26 +57,6 @@
 #include "stats.h"
 #include "autogroup.h"
 
-/*
- * Targeted preemption latency for CPU-bound tasks:
- *
- * NOTE: this latency value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS are of variable length
- * and have no persistent notion like in traditional, time-slice
- * based scheduling concepts.
- *
- * (to see the precise effective timeslice length of your workload,
- *  run vmstat and monitor the context-switches (cs) field)
- *
- * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
- */
-#ifdef CONFIG_CACHY
-unsigned int sysctl_sched_latency			= 3000000ULL;
-static unsigned int normalized_sysctl_sched_latency	= 3000000ULL;
-#else
-unsigned int sysctl_sched_latency			= 6000000ULL;
-static unsigned int normalized_sysctl_sched_latency	= 6000000ULL;
-#endif
 /*
  * The initial- and re-scaling of tunables is configurable
  *
@@ -94,26 +75,8 @@ unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
  *
  * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-#ifdef CONFIG_CACHY
-unsigned int sysctl_sched_min_granularity			= 400000ULL;
-static unsigned int normalized_sysctl_sched_min_granularity	= 400000ULL;
-#else
-unsigned int sysctl_sched_min_granularity			= 750000ULL;
-static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
-#endif
-
-/*
- * Minimal preemption granularity for CPU-bound SCHED_IDLE tasks.
- * Applies only when SCHED_IDLE tasks compete with normal tasks.
- *
- * (default: 0.75 msec)
- */
-unsigned int sysctl_sched_idle_min_granularity			= 750000ULL;
-
-/*
- * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity
- */
-static unsigned int sched_nr_latency = 8;
+unsigned int sysctl_sched_base_slice			= 750000ULL;
+static unsigned int normalized_sysctl_sched_base_slice	= 750000ULL;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -121,23 +84,6 @@ static unsigned int sched_nr_latency = 8;
  */
 unsigned int sysctl_sched_child_runs_first __read_mostly;
 
-/*
- * SCHED_OTHER wake-up granularity.
- *
- * This option delays the preemption effects of decoupled workloads
- * and reduces their over-scheduling. Synchronous workloads will still
- * have immediate wakeup/sleep latencies.
- *
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
- */
-#ifdef CONFIG_CACHY
-unsigned int sysctl_sched_wakeup_granularity			= 500000UL;
-static unsigned int normalized_sysctl_sched_wakeup_granularity	= 500000UL;
-#else
-unsigned int sysctl_sched_wakeup_granularity			= 1000000UL;
-static unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
-#endif
-
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
 int sched_thermal_decay_shift;
@@ -189,12 +135,8 @@ int __weak arch_asym_cpu_priority(int cpu)
  *
  * (default: 5 msec, units: microseconds)
  */
-#ifdef CONFIG_CACHY
-static unsigned int sysctl_sched_cfs_bandwidth_slice		= 3000UL;
-#else
 static unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
 #endif
-#endif
 
 #ifdef CONFIG_NUMA_BALANCING
 /* Restrict the NUMA promotion throughput (MB/s) for each target node. */
@@ -295,9 +237,7 @@ static void update_sysctl(void)
 
 #define SET_SYSCTL(name) \
 	(sysctl_##name = (factor) * normalized_sysctl_##name)
-	SET_SYSCTL(sched_min_granularity);
-	SET_SYSCTL(sched_latency);
-	SET_SYSCTL(sched_wakeup_granularity);
+	SET_SYSCTL(sched_base_slice);
 #undef SET_SYSCTL
 }
 
@@ -365,6 +305,16 @@ static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight
 	return mul_u64_u32_shr(delta_exec, fact, shift);
 }
 
+/*
+ * delta /= w
+ */
+static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
+{
+	if (unlikely(se->load.weight != NICE_0_LOAD))
+		delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
+
+	return delta;
+}
 
 const struct sched_class fair_sched_class;
 
@@ -619,35 +569,229 @@ static inline bool entity_before(const struct sched_entity *a,
 	return (s64)(a->vruntime - b->vruntime) < 0;
 }
 
+static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	return (s64)(se->vruntime - cfs_rq->min_vruntime);
+}
+
 #define __node_2_se(node) \
 	rb_entry((node), struct sched_entity, run_node)
 
-static void update_min_vruntime(struct cfs_rq *cfs_rq)
+/*
+ * Compute virtual time from the per-task service numbers:
+ *
+ * Fair schedulers conserve lag:
+ *
+ *   \Sum lag_i = 0
+ *
+ * Where lag_i is given by:
+ *
+ *   lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * Where S is the ideal service time and V is it's virtual time counterpart.
+ * Therefore:
+ *
+ *   \Sum lag_i = 0
+ *   \Sum w_i * (V - v_i) = 0
+ *   \Sum w_i * V - w_i * v_i = 0
+ *
+ * From which we can solve an expression for V in v_i (which we have in
+ * se->vruntime):
+ *
+ *       \Sum v_i * w_i   \Sum v_i * w_i
+ *   V = -------------- = --------------
+ *          \Sum w_i            W
+ *
+ * Specifically, this is the weighted average of all entity virtual runtimes.
+ *
+ * [[ NOTE: this is only equal to the ideal scheduler under the condition
+ *          that join/leave operations happen at lag_i = 0, otherwise the
+ *          virtual time has non-continguous motion equivalent to:
+ *
+ * 	      V +-= lag_i / W
+ *
+ * 	    Also see the comment in place_entity() that deals with this. ]]
+ *
+ * However, since v_i is u64, and the multiplcation could easily overflow
+ * transform it into a relative form that uses smaller quantities:
+ *
+ * Substitute: v_i == (v_i - v0) + v0
+ *
+ *     \Sum ((v_i - v0) + v0) * w_i   \Sum (v_i - v0) * w_i
+ * V = ---------------------------- = --------------------- + v0
+ *                  W                            W
+ *
+ * Which we track using:
+ *
+ *                    v0 := cfs_rq->min_vruntime
+ * \Sum (v_i - v0) * w_i := cfs_rq->avg_vruntime
+ *              \Sum w_i := cfs_rq->avg_load
+ *
+ * Since min_vruntime is a monotonic increasing variable that closely tracks
+ * the per-task service, these deltas: (v_i - v), will be in the order of the
+ * maximal (virtual) lag induced in the system due to quantisation.
+ *
+ * Also, we use scale_load_down() to reduce the size.
+ *
+ * As measured, the max (key * weight) value was ~44 bits for a kernel build.
+ */
+static void
+avg_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	unsigned long weight = scale_load_down(se->load.weight);
+	s64 key = entity_key(cfs_rq, se);
+
+	cfs_rq->avg_vruntime += key * weight;
+	cfs_rq->avg_slice += se->slice * weight;
+	cfs_rq->avg_load += weight;
+}
+
+static void
+avg_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	unsigned long weight = scale_load_down(se->load.weight);
+	s64 key = entity_key(cfs_rq, se);
+
+	cfs_rq->avg_vruntime -= key * weight;
+	cfs_rq->avg_slice -= se->slice * weight;
+	cfs_rq->avg_load -= weight;
+}
+
+static inline
+void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
+{
+	/*
+	 * v' = v + d ==> avg_vruntime' = avg_runtime - d*avg_load
+	 */
+	cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
+}
+
+u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline);
+	s64 avg = cfs_rq->avg_vruntime;
+	long load = cfs_rq->avg_load;
 
-	u64 vruntime = cfs_rq->min_vruntime;
+	if (curr && curr->on_rq) {
+		unsigned long weight = scale_load_down(curr->load.weight);
 
-	if (curr) {
-		if (curr->on_rq)
-			vruntime = curr->vruntime;
-		else
-			curr = NULL;
+		avg += entity_key(cfs_rq, curr) * weight;
+		load += weight;
 	}
 
-	if (leftmost) { /* non-empty tree */
-		struct sched_entity *se = __node_2_se(leftmost);
+	if (load)
+		avg = div_s64(avg, load);
 
-		if (!curr)
-			vruntime = se->vruntime;
-		else
-			vruntime = min_vruntime(vruntime, se->vruntime);
+	return cfs_rq->min_vruntime + avg;
+}
+
+/*
+ * lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * However, since V is approximated by the weighted average of all entities it
+ * is possible -- by addition/removal/reweight to the tree -- to move V around
+ * and end up with a larger lag than we started with.
+ *
+ * Limit this to either double the slice length with a minimum of TICK_NSEC
+ * since that is the timing granularity.
+ *
+ * EEVDF gives the following limit for a steady state system:
+ *
+ *   -r_max < lag < max(r_max, q)
+ *
+ * XXX could add max_slice to the augmented data to track this.
+ */
+void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 lag, limit;
+
+	SCHED_WARN_ON(!se->on_rq);
+	lag = avg_vruntime(cfs_rq) - se->vruntime;
+
+	limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+	se->vlag = clamp(lag, -limit, limit);
+}
+
+/*
+ * Entity is eligible once it received less service than it ought to have,
+ * eg. lag >= 0.
+ *
+ * lag_i = S - s_i = w_i*(V - v_i)
+ *
+ * lag_i >= 0 -> V >= v_i
+ *
+ *     \Sum (v_i - v)*w_i
+ * V = ------------------ + v
+ *          \Sum w_i
+ *
+ * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i)
+ *
+ * Note: using 'avg_vruntime() > se->vruntime' is inacurate due
+ *       to the loss in precision caused by the division.
+ */
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct sched_entity *curr = cfs_rq->curr;
+	s64 avg = cfs_rq->avg_vruntime;
+	long load = cfs_rq->avg_load;
+
+	if (curr && curr->on_rq) {
+		unsigned long weight = scale_load_down(curr->load.weight);
+
+		avg += entity_key(cfs_rq, curr) * weight;
+		load += weight;
 	}
 
-	/* ensure we never gain time by being placed backwards. */
-	u64_u32_store(cfs_rq->min_vruntime,
-		      max_vruntime(cfs_rq->min_vruntime, vruntime));
+	return avg >= entity_key(cfs_rq, se) * load;
+}
+
+static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
+{
+	u64 min_vruntime = cfs_rq->min_vruntime;
+	/*
+	 * open coded max_vruntime() to allow updating avg_vruntime
+	 */
+	s64 delta = (s64)(vruntime - min_vruntime);
+	if (delta > 0) {
+		avg_vruntime_update(cfs_rq, delta);
+		min_vruntime = vruntime;
+	}
+	return min_vruntime;
+}
+
+static void update_min_vruntime(struct cfs_rq *cfs_rq)
+{
+	if (sched_feat(MINIMAL_VA)) {
+		u64 vruntime = avg_vruntime(cfs_rq);
+		s64 delta = (s64)(vruntime - cfs_rq->min_vruntime);
+
+		avg_vruntime_update(cfs_rq, delta);
+
+		u64_u32_store(cfs_rq->min_vruntime, vruntime);
+	} else {
+		struct sched_entity *se = __pick_first_entity(cfs_rq);
+		struct sched_entity *curr = cfs_rq->curr;
+
+		u64 vruntime = cfs_rq->min_vruntime;
+
+		if (curr) {
+			if (curr->on_rq)
+				vruntime = curr->vruntime;
+			else
+				curr = NULL;
+		}
+
+		if (se) {
+			if (!curr)
+				vruntime = se->vruntime;
+			else
+				vruntime = min_vruntime(vruntime, se->vruntime);
+		}
+
+		/* ensure we never gain time by being placed backwards. */
+		u64_u32_store(cfs_rq->min_vruntime,
+				__update_min_vruntime(cfs_rq, vruntime));
+	}
 }
 
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -655,17 +799,51 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
 	return entity_before(__node_2_se(a), __node_2_se(b));
 }
 
+#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+
+static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+{
+	if (node) {
+		struct sched_entity *rse = __node_2_se(node);
+		if (deadline_gt(min_deadline, se, rse))
+			se->min_deadline = rse->min_deadline;
+	}
+}
+
+/*
+ * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ */
+static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+{
+	u64 old_min_deadline = se->min_deadline;
+	struct rb_node *node = &se->run_node;
+
+	se->min_deadline = se->deadline;
+	__update_min_deadline(se, node->rb_right);
+	__update_min_deadline(se, node->rb_left);
+
+	return se->min_deadline == old_min_deadline;
+}
+
+RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
+		     run_node, min_deadline, min_deadline_update);
+
 /*
  * Enqueue an entity into the rb-tree:
  */
 static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	rb_add_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less);
+	avg_vruntime_add(cfs_rq, se);
+	se->min_deadline = se->deadline;
+	rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
+				__entity_less, &min_deadline_cb);
 }
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	rb_erase_cached(&se->run_node, &cfs_rq->tasks_timeline);
+	rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
+				  &min_deadline_cb);
+	avg_vruntime_sub(cfs_rq, se);
 }
 
 struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
@@ -678,14 +856,81 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 	return __node_2_se(left);
 }
 
-static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+/*
+ * Earliest Eligible Virtual Deadline First
+ *
+ * In order to provide latency guarantees for different request sizes
+ * EEVDF selects the best runnable task from two criteria:
+ *
+ *  1) the task must be eligible (must be owed service)
+ *
+ *  2) from those tasks that meet 1), we select the one
+ *     with the earliest virtual deadline.
+ *
+ * We can do this in O(log n) time due to an augmented RB-tree. The
+ * tree keeps the entries sorted on service, but also functions as a
+ * heap based on the deadline by keeping:
+ *
+ *  se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ *
+ * Which allows an EDF like search on (sub)trees.
+ */
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 {
-	struct rb_node *next = rb_next(&se->run_node);
+	struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+	struct sched_entity *curr = cfs_rq->curr;
+	struct sched_entity *best = NULL;
 
-	if (!next)
-		return NULL;
+	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
+		curr = NULL;
+
+	while (node) {
+		struct sched_entity *se = __node_2_se(node);
+
+		/*
+		 * If this entity is not eligible, try the left subtree.
+		 */
+		if (!entity_eligible(cfs_rq, se)) {
+			node = node->rb_left;
+			continue;
+		}
 
-	return __node_2_se(next);
+		/*
+		 * If this entity has an earlier deadline than the previous
+		 * best, take this one. If it also has the earliest deadline
+		 * of its subtree, we're done.
+		 */
+		if (!best || deadline_gt(deadline, best, se)) {
+			best = se;
+			if (best->deadline == best->min_deadline)
+				break;
+		}
+
+		/*
+		 * If the earlest deadline in this subtree is in the fully
+		 * eligible left half of our space, go there.
+		 */
+		if (node->rb_left &&
+		    __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
+			node = node->rb_left;
+			continue;
+		}
+
+		node = node->rb_right;
+	}
+
+	if (!best || (curr && deadline_gt(deadline, best, curr)))
+		best = curr;
+
+	if (unlikely(!best)) {
+		struct sched_entity *left = __pick_first_entity(cfs_rq);
+		if (left) {
+			pr_err("EEVDF scheduling fail, picking leftmost\n");
+			return left;
+		}
+	}
+
+	return best;
 }
 
 #ifdef CONFIG_SCHED_DEBUG
@@ -707,104 +952,43 @@ int sched_update_scaling(void)
 {
 	unsigned int factor = get_update_sysctl_factor();
 
-	sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
-					sysctl_sched_min_granularity);
-
 #define WRT_SYSCTL(name) \
 	(normalized_sysctl_##name = sysctl_##name / (factor))
-	WRT_SYSCTL(sched_min_granularity);
-	WRT_SYSCTL(sched_latency);
-	WRT_SYSCTL(sched_wakeup_granularity);
+	WRT_SYSCTL(sched_base_slice);
 #undef WRT_SYSCTL
 
 	return 0;
 }
 #endif
 
-/*
- * delta /= w
- */
-static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se)
+void set_latency_fair(struct sched_entity *se, int prio)
 {
-	if (unlikely(se->load.weight != NICE_0_LOAD))
-		delta = __calc_delta(delta, NICE_0_LOAD, &se->load);
-
-	return delta;
-}
+	u32 weight = sched_prio_to_weight[prio];
+	u64 base = sysctl_sched_base_slice;
 
-/*
- * The idea is to set a period in which each task runs once.
- *
- * When there are too many tasks (sched_nr_latency) we have to stretch
- * this period because otherwise the slices get too small.
- *
- * p = (nr <= nl) ? l : l*nr/nl
- */
-static u64 __sched_period(unsigned long nr_running)
-{
-	if (unlikely(nr_running > sched_nr_latency))
-		return nr_running * sysctl_sched_min_granularity;
-	else
-		return sysctl_sched_latency;
+	/*
+	 * For EEVDF the virtual time slope is determined by w_i (iow.
+	 * nice) while the request time r_i is determined by
+	 * latency-nice.
+	 *
+	 * Smaller request gets better latency.
+	 */
+	se->slice = div_u64(base << SCHED_FIXEDPOINT_SHIFT, weight);
 }
 
-static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq);
-
 /*
- * We calculate the wall-time slice from the period by taking a part
- * proportional to the weight.
- *
- * s = p*P[w/rw]
+ * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
+ * this is probably good enough.
  */
-static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned int nr_running = cfs_rq->nr_running;
-	struct sched_entity *init_se = se;
-	unsigned int min_gran;
-	u64 slice;
-
-	if (sched_feat(ALT_PERIOD))
-		nr_running = rq_of(cfs_rq)->cfs.h_nr_running;
-
-	slice = __sched_period(nr_running + !se->on_rq);
-
-	for_each_sched_entity(se) {
-		struct load_weight *load;
-		struct load_weight lw;
-		struct cfs_rq *qcfs_rq;
-
-		qcfs_rq = cfs_rq_of(se);
-		load = &qcfs_rq->load;
-
-		if (unlikely(!se->on_rq)) {
-			lw = qcfs_rq->load;
-
-			update_load_add(&lw, se->load.weight);
-			load = &lw;
-		}
-		slice = __calc_delta(slice, se->load.weight, load);
-	}
-
-	if (sched_feat(BASE_SLICE)) {
-		if (se_is_idle(init_se) && !sched_idle_cfs_rq(cfs_rq))
-			min_gran = sysctl_sched_idle_min_granularity;
-		else
-			min_gran = sysctl_sched_min_granularity;
-
-		slice = max_t(u64, slice, min_gran);
-	}
-
-	return slice;
-}
+	if ((s64)(se->vruntime - se->deadline) < 0)
+		return;
 
-/*
- * We calculate the vruntime slice of a to-be-inserted task.
- *
- * vs = s/w
- */
-static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	return calc_delta_fair(sched_slice(cfs_rq, se), se);
+	/*
+	 * EEVDF: vd_i = ve_i + r_i / w_i
+	 */
+	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
 }
 
 #include "pelt.h"
@@ -939,6 +1123,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
+	update_deadline(cfs_rq, curr);
 	update_min_vruntime(cfs_rq);
 
 	if (entity_is_task(curr)) {
@@ -3336,16 +3521,28 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			    unsigned long weight)
 {
+	unsigned long old_weight = se->load.weight;
+
 	if (se->on_rq) {
 		/* commit outstanding execution time */
 		if (cfs_rq->curr == se)
 			update_curr(cfs_rq);
+		else
+			avg_vruntime_sub(cfs_rq, se);
 		update_load_sub(&cfs_rq->load, se->load.weight);
 	}
 	dequeue_load_avg(cfs_rq, se);
 
 	update_load_set(&se->load, weight);
 
+	if (!se->on_rq) {
+		/*
+		 * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v),
+		 * we need to scale se->vlag when w_i changes.
+		 */
+		se->vlag = div_s64(se->vlag * old_weight, weight);
+	}
+
 #ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
@@ -3355,9 +3552,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 #endif
 
 	enqueue_load_avg(cfs_rq, se);
-	if (se->on_rq)
+	if (se->on_rq) {
 		update_load_add(&cfs_rq->load, se->load.weight);
-
+		if (cfs_rq->curr != se)
+			avg_vruntime_add(cfs_rq, se);
+	}
 }
 
 void reweight_task(struct task_struct *p, int prio)
@@ -4653,158 +4852,168 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 
 #endif /* CONFIG_SMP */
 
-static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-#ifdef CONFIG_SCHED_DEBUG
-	s64 d = se->vruntime - cfs_rq->min_vruntime;
-
-	if (d < 0)
-		d = -d;
-
-	if (d > 3*sysctl_sched_latency)
-		schedstat_inc(cfs_rq->nr_spread_over);
-#endif
-}
-
-static inline bool entity_is_long_sleeper(struct sched_entity *se)
+static void
+place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	struct cfs_rq *cfs_rq;
-	u64 sleep_time;
+	u64 vslice = calc_delta_fair(se->slice, se);
+	u64 vruntime = avg_vruntime(cfs_rq);
+	s64 lag = 0;
 
-	if (se->exec_start == 0)
-		return false;
+	/*
+	 * Due to how V is constructed as the weighted average of entities,
+	 * adding tasks with positive lag, or removing tasks with negative lag
+	 * will move 'time' backwards, this can screw around with the lag of
+	 * other tasks.
+	 *
+	 * EEVDF: placement strategy #1 / #2
+	 */
+	if (sched_feat(PLACE_LAG) && cfs_rq->nr_running) {
+		struct sched_entity *curr = cfs_rq->curr;
+		unsigned long load;
 
-	cfs_rq = cfs_rq_of(se);
+		lag = se->vlag;
 
-	sleep_time = rq_clock_task(rq_of(cfs_rq));
+		/*
+		 * For latency sensitive tasks; those that have a shorter than
+		 * average slice and do not fully consume the slice, transition
+		 * to EEVDF placement strategy #2.
+		 */
+		if (sched_feat(PLACE_FUDGE) &&
+		    cfs_rq->avg_slice > se->slice * cfs_rq->avg_load) {
+			lag += vslice;
+			if (lag > 0)
+				lag = 0;
+		}
 
-	/* Happen while migrating because of clock task divergence */
-	if (sleep_time <= se->exec_start)
-		return false;
+		/*
+		 * If we want to place a task and preserve lag, we have to
+		 * consider the effect of the new entity on the weighted
+		 * average and compensate for this, otherwise lag can quickly
+		 * evaporate.
+		 *
+		 * Lag is defined as:
+		 *
+		 *   lag_i = S - s_i = w_i * (V - v_i)
+		 *
+		 * To avoid the 'w_i' term all over the place, we only track
+		 * the virtual lag:
+		 *
+		 *   vl_i = V - v_i <=> v_i = V - vl_i
+		 *
+		 * And we take V to be the weighted average of all v:
+		 *
+		 *   V = (\Sum w_j*v_j) / W
+		 *
+		 * Where W is: \Sum w_j
+		 *
+		 * Then, the weighted average after adding an entity with lag
+		 * vl_i is given by:
+		 *
+		 *   V' = (\Sum w_j*v_j + w_i*v_i) / (W + w_i)
+		 *      = (W*V + w_i*(V - vl_i)) / (W + w_i)
+		 *      = (W*V + w_i*V - w_i*vl_i) / (W + w_i)
+		 *      = (V*(W + w_i) - w_i*l) / (W + w_i)
+		 *      = V - w_i*vl_i / (W + w_i)
+		 *
+		 * And the actual lag after adding an entity with vl_i is:
+		 *
+		 *   vl'_i = V' - v_i
+		 *         = V - w_i*vl_i / (W + w_i) - (V - vl_i)
+		 *         = vl_i - w_i*vl_i / (W + w_i)
+		 *
+		 * Which is strictly less than vl_i. So in order to preserve lag
+		 * we should inflate the lag before placement such that the
+		 * effective lag after placement comes out right.
+		 *
+		 * As such, invert the above relation for vl'_i to get the vl_i
+		 * we need to use such that the lag after placement is the lag
+		 * we computed before dequeue.
+		 *
+		 *   vl'_i = vl_i - w_i*vl_i / (W + w_i)
+		 *         = ((W + w_i)*vl_i - w_i*vl_i) / (W + w_i)
+		 *
+		 *   (W + w_i)*vl'_i = (W + w_i)*vl_i - w_i*vl_i
+		 *                   = W*vl_i
+		 *
+		 *   vl_i = (W + w_i)*vl'_i / W
+		 */
+		load = cfs_rq->avg_load;
+		if (curr && curr->on_rq)
+			load += scale_load_down(curr->load.weight);
 
-	sleep_time -= se->exec_start;
-	if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD)))
-		return true;
+		lag *= load + scale_load_down(se->load.weight);
+		if (WARN_ON_ONCE(!load))
+			load = 1;
+		lag = div_s64(lag, load);
 
-	return false;
-}
+		vruntime -= lag;
+	}
 
-static void
-place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
-{
-	u64 vruntime = cfs_rq->min_vruntime;
+	/*
+	 * Base the deadline on the 'normal' EEVDF placement policy in an
+	 * attempt to not let the bonus crud below wreck things completely.
+	 */
+	se->deadline = vruntime;
 
 	/*
-	 * The 'current' period is already promised to the current tasks,
-	 * however the extra weight of the new task will slow them down a
-	 * little, place the new task so that it fits in the slot that
-	 * stays open at the end.
+	 * The whole 'sleeper' bonus hack... :-/ This is strictly unfair.
+	 *
+	 * By giving a sleeping task a little boost, it becomes possible for a
+	 * 50% task to compete equally with a 100% task. That is, strictly fair
+	 * that setup would result in a 67% / 33% split. Sleeper bonus will
+	 * change that to 50% / 50%.
+	 *
+	 * This thing hurts my brain, because tasks leaving with negative lag
+	 * will move 'time' backward, so comparing against a historical
+	 * se->vruntime is dodgy as heck.
 	 */
-	if (initial && sched_feat(START_DEBIT))
-		vruntime += sched_vslice(cfs_rq, se);
+	if (sched_feat(PLACE_BONUS) &&
+	    (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED)) {
+		/*
+		 * If se->vruntime is ahead of vruntime, something dodgy
+		 * happened and we cannot give bonus due to not having valid
+		 * history.
+		 */
+		if ((s64)(se->vruntime - vruntime) < 0) {
+			vruntime -= se->slice/2;
+			vruntime = max_vruntime(se->vruntime, vruntime);
+		}
+	}
 
-	/* sleeps up to a single latency don't count. */
-	if (!initial) {
-		unsigned long thresh;
+	se->vruntime = vruntime;
 
-		if (se_is_idle(se))
-			thresh = sysctl_sched_min_granularity;
-		else
-			thresh = sysctl_sched_latency;
+	/*
+	 * When joining the competition; the exisiting tasks will be,
+	 * on average, halfway through their slice, as such start tasks
+	 * off with half a slice to ease into the competition.
+	 */
+	if (sched_feat(PLACE_DEADLINE_INITIAL) && (flags & ENQUEUE_INITIAL))
+		vslice /= 2;
 
-		/*
-		 * Halve their sleep time's effect, to allow
-		 * for a gentler effect of sleepers:
-		 */
-		if (sched_feat(GENTLE_FAIR_SLEEPERS))
-			thresh >>= 1;
-
-		vruntime -= thresh;
-	}
-
-	/*
-	 * Pull vruntime of the entity being placed to the base level of
-	 * cfs_rq, to prevent boosting it if placed backwards.
-	 * However, min_vruntime can advance much faster than real time, with
-	 * the extreme being when an entity with the minimal weight always runs
-	 * on the cfs_rq. If the waking entity slept for a long time, its
-	 * vruntime difference from min_vruntime may overflow s64 and their
-	 * comparison may get inversed, so ignore the entity's original
-	 * vruntime in that case.
-	 * The maximal vruntime speedup is given by the ratio of normal to
-	 * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES.
-	 * When placing a migrated waking entity, its exec_start has been set
-	 * from a different rq. In order to take into account a possible
-	 * divergence between new and prev rq's clocks task because of irq and
-	 * stolen time, we take an additional margin.
-	 * So, cutting off on the sleep time of
-	 *     2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days
-	 * should be safe.
-	 */
-	if (entity_is_long_sleeper(se))
-		se->vruntime = vruntime;
-	else
-		se->vruntime = max_vruntime(se->vruntime, vruntime);
+	/*
+	 * EEVDF: vd_i = ve_i + r_i/w_i
+	 */
+	se->deadline += vslice;
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
 
 static inline bool cfs_bandwidth_used(void);
 
-/*
- * MIGRATION
- *
- *	dequeue
- *	  update_curr()
- *	    update_min_vruntime()
- *	  vruntime -= min_vruntime
- *
- *	enqueue
- *	  update_curr()
- *	    update_min_vruntime()
- *	  vruntime += min_vruntime
- *
- * this way the vruntime transition between RQs is done when both
- * min_vruntime are up-to-date.
- *
- * WAKEUP (remote)
- *
- *	->migrate_task_rq_fair() (p->state == TASK_WAKING)
- *	  vruntime -= min_vruntime
- *
- *	enqueue
- *	  update_curr()
- *	    update_min_vruntime()
- *	  vruntime += min_vruntime
- *
- * this way we don't have the most up-to-date min_vruntime on the originating
- * CPU and an up-to-date min_vruntime on the destination CPU.
- */
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED);
 	bool curr = cfs_rq->curr == se;
 
 	/*
 	 * If we're the current task, we must renormalise before calling
 	 * update_curr().
 	 */
-	if (renorm && curr)
-		se->vruntime += cfs_rq->min_vruntime;
+	if (curr)
+		place_entity(cfs_rq, se, flags);
 
 	update_curr(cfs_rq);
 
-	/*
-	 * Otherwise, renormalise after, such that we're placed at the current
-	 * moment in time, instead of some random moment in the past. Being
-	 * placed in the past could significantly boost this task to the
-	 * fairness detriment of existing tasks.
-	 */
-	if (renorm && !curr)
-		se->vruntime += cfs_rq->min_vruntime;
-
 	/*
 	 * When enqueuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
@@ -4816,18 +5025,28 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH);
 	se_update_runnable(se);
+	/*
+	 * XXX update_load_avg() above will have attached us to the pelt sum;
+	 * but update_cfs_group() here will re-adjust the weight and have to
+	 * undo/redo all that. Seems wasteful.
+	 */
 	update_cfs_group(se);
+
+	/*
+	 * XXX now that the entity has been re-weighted, and it's lag adjusted,
+	 * we can place the entity.
+	 */
+	if (!curr)
+		place_entity(cfs_rq, se, flags);
+
 	account_entity_enqueue(cfs_rq, se);
 
-	if (flags & ENQUEUE_WAKEUP)
-		place_entity(cfs_rq, se, 0);
 	/* Entity has migrated, no longer consider this task hot */
 	if (flags & ENQUEUE_MIGRATED)
 		se->exec_start = 0;
 
 	check_schedstat_required();
 	update_stats_enqueue_fair(cfs_rq, se, flags);
-	check_spread(cfs_rq, se);
 	if (!curr)
 		__enqueue_entity(cfs_rq, se);
 	se->on_rq = 1;
@@ -4839,17 +5058,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	}
 }
 
-static void __clear_buddies_last(struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->last != se)
-			break;
-
-		cfs_rq->last = NULL;
-	}
-}
-
 static void __clear_buddies_next(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
@@ -4861,27 +5069,10 @@ static void __clear_buddies_next(struct sched_entity *se)
 	}
 }
 
-static void __clear_buddies_skip(struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->skip != se)
-			break;
-
-		cfs_rq->skip = NULL;
-	}
-}
-
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (cfs_rq->last == se)
-		__clear_buddies_last(se);
-
 	if (cfs_rq->next == se)
 		__clear_buddies_next(se);
-
-	if (cfs_rq->skip == se)
-		__clear_buddies_skip(se);
 }
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -4915,20 +5106,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	clear_buddies(cfs_rq, se);
 
+	update_entity_lag(cfs_rq, se);
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	se->on_rq = 0;
 	account_entity_dequeue(cfs_rq, se);
 
-	/*
-	 * Normalize after update_curr(); which will also have moved
-	 * min_vruntime if @se is the one holding it back. But before doing
-	 * update_min_vruntime() again, which will discount @se's position and
-	 * can move min_vruntime forward still more.
-	 */
-	if (!(flags & DEQUEUE_SLEEP))
-		se->vruntime -= cfs_rq->min_vruntime;
-
 	/* return excess runtime on last dequeue */
 	return_cfs_rq_runtime(cfs_rq);
 
@@ -4953,44 +5136,14 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 static void
 check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	unsigned long ideal_runtime, delta_exec;
-	struct sched_entity *se;
-	s64 delta;
-
-	/*
-	 * When many tasks blow up the sched_period; it is possible that
-	 * sched_slice() reports unusually large results (when many tasks are
-	 * very light for example). Therefore impose a maximum.
-	 */
-	ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency);
-
-	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	if (delta_exec > ideal_runtime) {
+	if (pick_eevdf(cfs_rq) != curr) {
 		resched_curr(rq_of(cfs_rq));
 		/*
 		 * The current task ran long enough, ensure it doesn't get
 		 * re-elected due to buddy favours.
 		 */
 		clear_buddies(cfs_rq, curr);
-		return;
 	}
-
-	/*
-	 * Ensure that a task that missed wakeup preemption by a
-	 * narrow margin doesn't have to wait for a full slice.
-	 * This also mitigates buddy induced latencies under load.
-	 */
-	if (delta_exec < sysctl_sched_min_granularity)
-		return;
-
-	se = __pick_first_entity(cfs_rq);
-	delta = curr->vruntime - se->vruntime;
-
-	if (delta < 0)
-		return;
-
-	if (delta > ideal_runtime)
-		resched_curr(rq_of(cfs_rq));
 }
 
 static void
@@ -5031,9 +5184,6 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-
 /*
  * Pick the next process, keeping these things in mind, in this order:
  * 1) keep things fair between processes/task groups
@@ -5044,50 +5194,14 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *
 pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	struct sched_entity *left = __pick_first_entity(cfs_rq);
-	struct sched_entity *se;
-
-	/*
-	 * If curr is set we have to see if its left of the leftmost entity
-	 * still in the tree, provided there was anything in the tree at all.
-	 */
-	if (!left || (curr && entity_before(curr, left)))
-		left = curr;
-
-	se = left; /* ideally we run the leftmost entity */
-
 	/*
-	 * Avoid running the skip buddy, if running something else can
-	 * be done without getting too unfair.
+	 * Enabling NEXT_BUDDY will affect latency but not fairness.
 	 */
-	if (cfs_rq->skip && cfs_rq->skip == se) {
-		struct sched_entity *second;
-
-		if (se == curr) {
-			second = __pick_first_entity(cfs_rq);
-		} else {
-			second = __pick_next_entity(se);
-			if (!second || (curr && entity_before(curr, second)))
-				second = curr;
-		}
-
-		if (second && wakeup_preempt_entity(second, left) < 1)
-			se = second;
-	}
+	if (sched_feat(NEXT_BUDDY) &&
+	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
+		return cfs_rq->next;
 
-	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) {
-		/*
-		 * Someone really wants this to run. If it's not unfair, run it.
-		 */
-		se = cfs_rq->next;
-	} else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) {
-		/*
-		 * Prefer last buddy, try to return the CPU to a preempted task.
-		 */
-		se = cfs_rq->last;
-	}
-
-	return se;
+	return pick_eevdf(cfs_rq);
 }
 
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -5104,8 +5218,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
 	/* throttle cfs_rqs exceeding runtime */
 	check_cfs_rq_runtime(cfs_rq);
 
-	check_spread(cfs_rq, prev);
-
 	if (prev->on_rq) {
 		update_stats_wait_start_fair(cfs_rq, prev);
 		/* Put 'current' back into the tree. */
@@ -6149,13 +6261,12 @@ static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	SCHED_WARN_ON(task_rq(p) != rq);
 
 	if (rq->cfs.h_nr_running > 1) {
-		u64 slice = sched_slice(cfs_rq, se);
 		u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+		u64 slice = se->slice;
 		s64 delta = slice - ran;
 
 		if (delta < 0) {
@@ -6179,8 +6290,7 @@ static void hrtick_update(struct rq *rq)
 	if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class)
 		return;
 
-	if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
-		hrtick_start_fair(rq, curr);
+	hrtick_start_fair(rq, curr);
 }
 #else /* !CONFIG_SCHED_HRTICK */
 static inline void
@@ -6221,17 +6331,6 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
-/*
- * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use
- * of idle_nr_running, which does not consider idle descendants of normal
- * entities.
- */
-static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq)
-{
-	return cfs_rq->nr_running &&
-		cfs_rq->nr_running == cfs_rq->idle_nr_running;
-}
-
 #ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
@@ -6333,18 +6432,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 static void set_next_buddy(struct sched_entity *se);
 
-static inline void dur_avg_update(struct task_struct *p, bool task_sleep)
-{
-	u64 dur;
-
-	if (!task_sleep)
-		return;
-
-	dur = p->se.sum_exec_runtime - p->se.prev_sleep_sum_runtime;
-	p->se.prev_sleep_sum_runtime = p->se.sum_exec_runtime;
-	update_avg(&p->se.dur_avg, dur);
-}
-
 /*
  * The dequeue_task method is called before nr_running is
  * decreased. We remove the task from the rbtree and
@@ -6417,7 +6504,6 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 dequeue_throttle:
 	util_est_update(&rq->cfs, p, task_sleep);
-	dur_avg_update(p, task_sleep);
 	hrtick_update(rq);
 }
 
@@ -6551,23 +6637,6 @@ static int wake_wide(struct task_struct *p)
 	return 1;
 }
 
-/*
- * If a task switches in and then voluntarily relinquishes the
- * CPU quickly, it is regarded as a short duration task.
- *
- * SIS_SHORT tries to wake up the short wakee on current CPU. This
- * aims to avoid race condition among CPUs due to frequent context
- * switch. Besides, the candidate short task should not be the one
- * that wakes up more than one tasks, otherwise SIS_SHORT might
- * stack too many tasks on current CPU.
- */
-static inline int is_short_task(struct task_struct *p)
-{
-	return sched_feat(SIS_SHORT) && !p->wakee_flips &&
-	       p->se.dur_avg &&
-	       ((p->se.dur_avg * 8) < sysctl_sched_min_granularity);
-}
-
 /*
  * The purpose of wake_affine() is to quickly determine on which CPU we can run
  * soonest. For the purpose of speed we only consider the waking and previous
@@ -6604,11 +6673,6 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (available_idle_cpu(prev_cpu))
 		return prev_cpu;
 
-	/* The only running task is a short duration one. */
-	if (cpu_rq(this_cpu)->nr_running == 1 &&
-	    is_short_task(rcu_dereference(cpu_curr(this_cpu))))
-		return this_cpu;
-
 	return nr_cpumask_bits;
 }
 
@@ -6983,20 +7047,6 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 			/* overloaded LLC is unlikely to have idle cpu/core */
 			if (nr == 1)
 				return -1;
-
-			/*
-			 * If the scan number suggested by SIS_UTIL is smaller
-			 * than 60% of llc_weight, it indicates a util_avg% higher
-			 * than 50%. System busier than this could lower its bar to
-			 * choose a compromised "idle" CPU. This co-exists with
-			 * !has_idle_core to not stack too many tasks on one CPU.
-			 */
-			if (!has_idle_core && this == target &&
-			    (5 * nr < 3 * sd->span_weight) &&
-			    cpu_rq(target)->nr_running <= 1 &&
-			    is_short_task(p) &&
-			    is_short_task(rcu_dereference(cpu_curr(target))))
-				return target;
 		}
 	}
 
@@ -7729,18 +7779,6 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 {
 	struct sched_entity *se = &p->se;
 
-	/*
-	 * As blocked tasks retain absolute vruntime the migration needs to
-	 * deal with this by subtracting the old and adding the new
-	 * min_vruntime -- the latter is done by enqueue_entity() when placing
-	 * the task on the new runqueue.
-	 */
-	if (READ_ONCE(p->__state) == TASK_WAKING) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
-		se->vruntime -= u64_u32_load(cfs_rq->min_vruntime);
-	}
-
 	if (!task_on_rq_migrating(p)) {
 		remove_entity_load_avg(se);
 
@@ -7778,66 +7816,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 }
 #endif /* CONFIG_SMP */
 
-static unsigned long wakeup_gran(struct sched_entity *se)
-{
-	unsigned long gran = sysctl_sched_wakeup_granularity;
-
-	/*
-	 * Since its curr running now, convert the gran from real-time
-	 * to virtual-time in his units.
-	 *
-	 * By using 'se' instead of 'curr' we penalize light tasks, so
-	 * they get preempted easier. That is, if 'se' < 'curr' then
-	 * the resulting gran will be larger, therefore penalizing the
-	 * lighter, if otoh 'se' > 'curr' then the resulting gran will
-	 * be smaller, again penalizing the lighter task.
-	 *
-	 * This is especially important for buddies when the leftmost
-	 * task is higher priority than the buddy.
-	 */
-	return calc_delta_fair(gran, se);
-}
-
-/*
- * Should 'se' preempt 'curr'.
- *
- *             |s1
- *        |s2
- *   |s3
- *         g
- *      |<--->|c
- *
- *  w(c, s1) = -1
- *  w(c, s2) =  0
- *  w(c, s3) =  1
- *
- */
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
-{
-	s64 gran, vdiff = curr->vruntime - se->vruntime;
-
-	if (vdiff <= 0)
-		return -1;
-
-	gran = wakeup_gran(se);
-	if (vdiff > gran)
-		return 1;
-
-	return 0;
-}
-
-static void set_last_buddy(struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		if (SCHED_WARN_ON(!se->on_rq))
-			return;
-		if (se_is_idle(se))
-			return;
-		cfs_rq_of(se)->last = se;
-	}
-}
-
 static void set_next_buddy(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
@@ -7849,12 +7827,6 @@ static void set_next_buddy(struct sched_entity *se)
 	}
 }
 
-static void set_skip_buddy(struct sched_entity *se)
-{
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->skip = se;
-}
-
 /*
  * Preempt the current task with a newly woken task if needed:
  */
@@ -7863,7 +7835,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-	int scale = cfs_rq->nr_running >= sched_nr_latency;
 	int next_buddy_marked = 0;
 	int cse_is_idle, pse_is_idle;
 
@@ -7879,7 +7850,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(throttled_hierarchy(cfs_rq_of(pse))))
 		return;
 
-	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
+	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) {
 		set_next_buddy(pse);
 		next_buddy_marked = 1;
 	}
@@ -7924,35 +7895,19 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (cse_is_idle != pse_is_idle)
 		return;
 
-	update_curr(cfs_rq_of(se));
-	if (wakeup_preempt_entity(se, pse) == 1) {
-		/*
-		 * Bias pick_next to pick the sched entity that is
-		 * triggering this preemption.
-		 */
-		if (!next_buddy_marked)
-			set_next_buddy(pse);
+	cfs_rq = cfs_rq_of(se);
+	update_curr(cfs_rq);
+
+	/*
+	 * XXX pick_eevdf(cfs_rq) != se ?
+	 */
+	if (pick_eevdf(cfs_rq) == pse)
 		goto preempt;
-	}
 
 	return;
 
 preempt:
 	resched_curr(rq);
-	/*
-	 * Only set the backward buddy when the current task is still
-	 * on the rq. This can happen when a wakeup gets interleaved
-	 * with schedule on the ->pre_schedule() or idle_balance()
-	 * point, either of which can * drop the rq lock.
-	 *
-	 * Also, during early boot the idle thread is in the fair class,
-	 * for obvious reasons its a bad idea to schedule back to it.
-	 */
-	if (unlikely(!se->on_rq || curr == rq->idle))
-		return;
-
-	if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
-		set_last_buddy(se);
 }
 
 #ifdef CONFIG_SMP
@@ -8153,8 +8108,6 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 
 /*
  * sched_yield() is very simple
- *
- * The magic of dealing with the ->skip buddy is in pick_next_entity.
  */
 static void yield_task_fair(struct rq *rq)
 {
@@ -8170,21 +8123,19 @@ static void yield_task_fair(struct rq *rq)
 
 	clear_buddies(cfs_rq, se);
 
-	if (curr->policy != SCHED_BATCH) {
-		update_rq_clock(rq);
-		/*
-		 * Update run-time statistics of the 'current'.
-		 */
-		update_curr(cfs_rq);
-		/*
-		 * Tell update_rq_clock() that we've just updated,
-		 * so we don't do microscopic update in schedule()
-		 * and double the fastpath cost.
-		 */
-		rq_clock_skip_update(rq);
-	}
+	update_rq_clock(rq);
+	/*
+	 * Update run-time statistics of the 'current'.
+	 */
+	update_curr(cfs_rq);
+	/*
+	 * Tell update_rq_clock() that we've just updated,
+	 * so we don't do microscopic update in schedule()
+	 * and double the fastpath cost.
+	 */
+	rq_clock_skip_update(rq);
 
-	set_skip_buddy(se);
+	se->deadline += calc_delta_fair(se->slice, se);
 }
 
 static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
@@ -8427,8 +8378,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 	 * Buddy candidates are cache hot:
 	 */
 	if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running &&
-			(&p->se == cfs_rq_of(&p->se)->next ||
-			 &p->se == cfs_rq_of(&p->se)->last))
+	    (&p->se == cfs_rq_of(&p->se)->next))
 		return 1;
 
 	if (sysctl_sched_migration_cost == -1)
@@ -11942,8 +11892,8 @@ static void rq_offline_fair(struct rq *rq)
 static inline bool
 __entity_slice_used(struct sched_entity *se, int min_nr_tasks)
 {
-	u64 slice = sched_slice(cfs_rq_of(se), se);
 	u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+	u64 slice = se->slice;
 
 	return (rtime * min_nr_tasks > slice);
 }
@@ -12087,8 +12037,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
  */
 static void task_fork_fair(struct task_struct *p)
 {
-	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
+	struct cfs_rq *cfs_rq;
 	struct rq *rq = this_rq();
 	struct rq_flags rf;
 
@@ -12097,22 +12047,9 @@ static void task_fork_fair(struct task_struct *p)
 
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
-	if (curr) {
+	if (curr)
 		update_curr(cfs_rq);
-		se->vruntime = curr->vruntime;
-	}
-	place_entity(cfs_rq, se, 1);
-
-	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
-		/*
-		 * Upon rescheduling, sched_class::put_prev_task() will place
-		 * 'current' within the tree based on its new key value.
-		 */
-		swap(curr->vruntime, se->vruntime);
-		resched_curr(rq);
-	}
-
-	se->vruntime -= cfs_rq->min_vruntime;
+	place_entity(cfs_rq, se, ENQUEUE_INITIAL);
 	rq_unlock(rq, &rf);
 }
 
@@ -12141,34 +12078,6 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 		check_preempt_curr(rq, p, 0);
 }
 
-static inline bool vruntime_normalized(struct task_struct *p)
-{
-	struct sched_entity *se = &p->se;
-
-	/*
-	 * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases,
-	 * the dequeue_entity(.flags=0) will already have normalized the
-	 * vruntime.
-	 */
-	if (p->on_rq)
-		return true;
-
-	/*
-	 * When !on_rq, vruntime of the task has usually NOT been normalized.
-	 * But there are some cases where it has already been normalized:
-	 *
-	 * - A forked child which is waiting for being woken up by
-	 *   wake_up_new_task().
-	 * - A task which has been woken up by try_to_wake_up() and
-	 *   waiting for actually being woken up by sched_ttwu_pending().
-	 */
-	if (!se->sum_exec_runtime ||
-	    (READ_ONCE(p->__state) == TASK_WAKING && p->sched_remote_wakeup))
-		return true;
-
-	return false;
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * Propagate the changes of the sched_entity across the tg tree to make it
@@ -12239,16 +12148,6 @@ static void attach_entity_cfs_rq(struct sched_entity *se)
 static void detach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-
-	if (!vruntime_normalized(p)) {
-		/*
-		 * Fix up our vruntime so that the current sleep doesn't
-		 * cause 'unlimited' sleep bonus.
-		 */
-		place_entity(cfs_rq, se, 0);
-		se->vruntime -= cfs_rq->min_vruntime;
-	}
 
 	detach_entity_cfs_rq(se);
 }
@@ -12256,12 +12155,8 @@ static void detach_task_cfs_rq(struct task_struct *p)
 static void attach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
-	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
 	attach_entity_cfs_rq(se);
-
-	if (!vruntime_normalized(p))
-		se->vruntime += cfs_rq->min_vruntime;
 }
 
 static void switched_from_fair(struct rq *rq, struct task_struct *p)
@@ -12372,6 +12267,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		goto err;
 
 	tg->shares = NICE_0_LOAD;
+	tg->latency_prio = DEFAULT_PRIO;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
@@ -12470,6 +12366,9 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	}
 
 	se->my_q = cfs_rq;
+
+	set_latency_fair(se, tg->latency_prio - MAX_RT_PRIO);
+
 	/* guarantee group entities always have weight */
 	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
@@ -12600,6 +12499,29 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	return 0;
 }
 
+int sched_group_set_latency(struct task_group *tg, int prio)
+{
+	int i;
+
+	if (tg == &root_task_group)
+		return -EINVAL;
+
+	mutex_lock(&shares_mutex);
+
+	if (tg->latency_prio == prio) {
+		mutex_unlock(&shares_mutex);
+		return 0;
+	}
+
+	tg->latency_prio = prio;
+
+	for_each_possible_cpu(i)
+		set_latency_fair(tg->se[i], prio - MAX_RT_PRIO);
+
+	mutex_unlock(&shares_mutex);
+	return 0;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 void free_fair_sched_group(struct task_group *tg) { }
@@ -12626,7 +12548,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 	 * idle runqueue:
 	 */
 	if (rq->cfs.load.weight)
-		rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
+		rr_interval = NS_TO_JIFFIES(se->slice);
 
 	return rr_interval;
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index efdc29c42161..d4b7d3f7c044 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,16 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Only give sleepers 50% of their service deficit. This allows
- * them to run sooner, but does not allow tons of sleepers to
- * rip the spread apart.
- */
-SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true)
 
 /*
- * Place new tasks ahead so that they do not starve already running
- * tasks
+ * Using the avg_vruntime, do the right thing and preserve lag across
+ * sleep+wake cycles. EEVDF placement strategy #1, #2 if disabled.
  */
-SCHED_FEAT(START_DEBIT, true)
+SCHED_FEAT(PLACE_LAG, true)
+SCHED_FEAT(PLACE_FUDGE, true)
+SCHED_FEAT(PLACE_DEADLINE_INITIAL, true)
+SCHED_FEAT(PLACE_BONUS, false)
+
+SCHED_FEAT(MINIMAL_VA, false)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
@@ -19,13 +18,6 @@ SCHED_FEAT(START_DEBIT, true)
  */
 SCHED_FEAT(NEXT_BUDDY, false)
 
-/*
- * Prefer to schedule the task that ran last (when we did
- * wake-preempt) as that likely will touch the same data, increases
- * cache locality.
- */
-SCHED_FEAT(LAST_BUDDY, true)
-
 /*
  * Consider buddies to be cache hot, decreases the likeliness of a
  * cache buddy being migrated away, increases cache locality.
@@ -62,7 +54,6 @@ SCHED_FEAT(TTWU_QUEUE, true)
  */
 SCHED_FEAT(SIS_PROP, false)
 SCHED_FEAT(SIS_UTIL, true)
-SCHED_FEAT(SIS_SHORT, true)
 
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls
@@ -99,6 +90,3 @@ SCHED_FEAT(UTIL_EST, true)
 SCHED_FEAT(UTIL_EST_FASTUP, true)
 
 SCHED_FEAT(LATENCY_WARN, false)
-
-SCHED_FEAT(ALT_PERIOD, true)
-SCHED_FEAT(BASE_SLICE, true)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7331d436ebc4..bfce45b21441 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -378,6 +378,8 @@ struct task_group {
 
 	/* A positive value indicates that this is a SCHED_IDLE group. */
 	int			idle;
+	/* latency priority of the group. */
+	int			latency_prio;
 
 #ifdef	CONFIG_SMP
 	/*
@@ -488,6 +490,8 @@ extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern int sched_group_set_idle(struct task_group *tg, long idle);
 
+extern int sched_group_set_latency(struct task_group *tg, int prio);
+
 #ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);
@@ -554,6 +558,10 @@ struct cfs_rq {
 	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
+	s64			avg_vruntime;
+	u64			avg_slice;
+	u64			avg_load;
+
 	u64			exec_clock;
 	u64			min_vruntime;
 #ifdef CONFIG_SCHED_CORE
@@ -573,8 +581,6 @@ struct cfs_rq {
 	 */
 	struct sched_entity	*curr;
 	struct sched_entity	*next;
-	struct sched_entity	*last;
-	struct sched_entity	*skip;
 
 #ifdef	CONFIG_SCHED_DEBUG
 	unsigned int		nr_spread_over;
@@ -2154,7 +2160,7 @@ extern const u32		sched_prio_to_wmult[40];
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
- *
+ * ENQUEUE_INITIAL   - place a new task (fork/clone)
  */
 
 #define DEQUEUE_SLEEP		0x01
@@ -2174,6 +2180,7 @@ extern const u32		sched_prio_to_wmult[40];
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
+#define ENQUEUE_INITIAL		0x80
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2476,10 +2483,7 @@ extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
 #ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_idle_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
+extern unsigned int sysctl_sched_base_slice;
 extern int sysctl_resched_latency_warn_ms;
 extern int sysctl_resched_latency_warn_once;
 
@@ -2492,6 +2496,8 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_hot_threshold;
 #endif
 
+extern void set_latency_fair(struct sched_entity *se, int prio);
+
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -3323,4 +3329,7 @@ static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *n
 static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) { }
 #endif
 
+extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
 #endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 3bac0a8ceab2..b2e932c25be6 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -132,6 +132,7 @@ struct clone_args {
 #define SCHED_FLAG_KEEP_PARAMS		0x10
 #define SCHED_FLAG_UTIL_CLAMP_MIN	0x20
 #define SCHED_FLAG_UTIL_CLAMP_MAX	0x40
+#define SCHED_FLAG_LATENCY_NICE		0x80
 
 #define SCHED_FLAG_KEEP_ALL	(SCHED_FLAG_KEEP_POLICY | \
 				 SCHED_FLAG_KEEP_PARAMS)
@@ -143,6 +144,7 @@ struct clone_args {
 			 SCHED_FLAG_RECLAIM		| \
 			 SCHED_FLAG_DL_OVERRUN		| \
 			 SCHED_FLAG_KEEP_ALL		| \
-			 SCHED_FLAG_UTIL_CLAMP)
+			 SCHED_FLAG_UTIL_CLAMP		| \
+			 SCHED_FLAG_LATENCY_NICE)
 
 #endif /* _UAPI_LINUX_SCHED_H */
-- 
2.40.0