linux-pikaos-template/patches/0004-eevdf.patch

From b6d3ec3be2639fe928a09b558e979c36b41ea63b Mon Sep 17 00:00:00 2001
From: Peter Jung <admin@ptr1337.dev>
Date: Sat, 11 Mar 2023 18:42:39 +0100
Subject: [PATCH] EEVDF

Ever since looking at the latency-nice patches, I've wondered if EEVDF would
not make more sense, and I did point Vincent at some older patches I had for
that (which is here his augmented rbtree thing comes from).

Also, since I really dislike the dual tree, I also figured we could dynamically
switch between an augmented tree and not (and while I have code for that,
that's not included in this posting because with the current results I don't
think we actually need this).

Anyway, since I'm somewhat under the weather, I spend last week desperately
trying to connect a small cluster of neurons in defiance of the snot overlord
and bring back the EEVDF patches from the dark crypts where they'd been
gathering cobwebs for the past 13 odd years.

By friday they worked well enough, and this morning (because obviously I forgot
the weekend is ideal to run benchmarks) I ran a bunch of hackbenck, netperf,
tbench and sysbench -- there's a bunch of wins and losses, but nothing that
indicates a total fail.

( in fact, some of the schbench results seem to indicate EEVDF schedules a lot
  more consistent than CFS and has a bunch of latency wins )

( hackbench also doesn't show the augmented tree and generally more expensive
  pick to be a loss, in fact it shows a slight win here )

  hackbech load + cyclictest --policy other results:

			EEVDF			 CFS

		# Min Latencies: 00053
  LNICE(19)	# Avg Latencies: 04350
		# Max Latencies: 76019

		# Min Latencies: 00052		00053
  LNICE(0)	# Avg Latencies: 00690		00687
		# Max Latencies: 14145		13913

		# Min Latencies: 00019
  LNICE(-19)	# Avg Latencies: 00261
		# Max Latencies: 05642

The nice -19 numbers aren't as pretty as Vincent's, but at the end I was going
cross-eyed from staring at tree prints and I just couldn't figure out where it
was going side-ways.

There's definitely more benchmarking/tweaking to be done (0-day already
reported a stress-ng loss), but if we can pull this off we can delete a whole
much of icky heuristics code. EEVDF is a much better defined policy than what
we currently have.

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                   |   8 +
 include/linux/sched/prio.h              |  27 ++
 include/uapi/linux/sched.h              |   4 +-
 include/uapi/linux/sched/types.h        |  19 +
 init/init_task.c                        |   1 +
 kernel/sched/core.c                     |  66 ++++
 kernel/sched/debug.c                    |  39 +-
 kernel/sched/fair.c                     | 486 ++++++++++++++++++++----
 kernel/sched/features.h                 |  10 +-
 kernel/sched/sched.h                    |  12 +
 tools/include/uapi/linux/sched.h        |   4 +-
 13 files changed, 614 insertions(+), 98 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 74cec76be9f2..2e511d4a4c6a 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1118,6 +1118,16 @@ 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 28ce1be0ba47..764df627c243 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;
 
@@ -555,6 +558,8 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				vruntime;
 	u64				prev_sum_exec_runtime;
+	s64				lag;
+	u64				slice;
 
 	u64				nr_migrations;
 	u64				prev_sleep_sum_runtime;
@@ -571,6 +576,8 @@ struct sched_entity {
 	/* cached value of my_q->h_nr_running */
 	unsigned long			runnable_weight;
 #endif
+	/* preemption offset in ns */
+	long				latency_offset;
 
 #ifdef CONFIG_SMP
 	/*
@@ -787,6 +794,7 @@ 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/linux/sched/prio.h b/include/linux/sched/prio.h
index ab83d85e1183..be79503d86af 100644
--- a/include/linux/sched/prio.h
+++ b/include/linux/sched/prio.h
@@ -42,4 +42,31 @@ static inline long rlimit_to_nice(long prio)
 	return (MAX_NICE - prio + 1);
 }
 
+/*
+ * Latency nice is meant to provide scheduler hints about the relative
+ * latency requirements of a task with respect to other tasks.
+ * Thus a task with latency_nice == 19 can be hinted as the task with no
+ * latency requirements, in contrast to the task with latency_nice == -20
+ * which should be given priority in terms of lower latency.
+ */
+#define MAX_LATENCY_NICE	19
+#define MIN_LATENCY_NICE	-20
+
+#define LATENCY_NICE_WIDTH	\
+	(MAX_LATENCY_NICE - MIN_LATENCY_NICE + 1)
+
+/*
+ * Default tasks should be treated as a task with latency_nice = 0.
+ */
+#define DEFAULT_LATENCY_NICE	0
+#define DEFAULT_LATENCY_PRIO	(DEFAULT_LATENCY_NICE + LATENCY_NICE_WIDTH/2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static latency [ 0..39 ],
+ * and back.
+ */
+#define NICE_TO_LATENCY(nice)	((nice) + DEFAULT_LATENCY_PRIO)
+#define LATENCY_TO_NICE(prio)	((prio) - DEFAULT_LATENCY_PRIO)
+
 #endif /* _LINUX_SCHED_PRIO_H */
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..071deff8dbd1 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_LATENCY_PRIO,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
 	.user_cpus_ptr	= NULL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5237639786b7..9db5f9ec9022 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1283,6 +1283,11 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	}
 }
 
+static void set_latency_offset(struct task_struct *p)
+{
+	p->se.latency_offset = calc_latency_offset(p->latency_prio);
+}
+
 #ifdef CONFIG_UCLAMP_TASK
 /*
  * Serializes updates of utilization clamp values
@@ -4431,8 +4436,11 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.vruntime			= 0;
 	p->se.dur_avg			= 0;
 	p->se.prev_sleep_sum_runtime	= 0;
+	p->se.lag			= 0;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+	set_latency_offset(p);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
 #endif
@@ -4684,6 +4692,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->prio = p->normal_prio = p->static_prio;
 		set_load_weight(p, false);
 
+		p->latency_prio = NICE_TO_LATENCY(0);
+		set_latency_offset(p);
+
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
 		 * fulfilled its duty:
@@ -7446,6 +7457,15 @@ 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) {
+		p->latency_prio = NICE_TO_LATENCY(attr->sched_latency_nice);
+		set_latency_offset(p);
+	}
+}
+
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -7586,6 +7606,13 @@ static int __sched_setscheduler(struct task_struct *p,
 			return retval;
 	}
 
+	if (attr->sched_flags & SCHED_FLAG_LATENCY_NICE) {
+		if (attr->sched_latency_nice > MAX_LATENCY_NICE)
+			return -EINVAL;
+		if (attr->sched_latency_nice < MIN_LATENCY_NICE)
+			return -EINVAL;
+	}
+
 	if (pi)
 		cpuset_read_lock();
 
@@ -7620,6 +7647,9 @@ 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 != LATENCY_TO_NICE(p->latency_prio))
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		retval = 0;
@@ -7708,6 +7738,7 @@ 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) {
@@ -7918,6 +7949,9 @@ 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?
@@ -8155,6 +8189,8 @@ 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 = LATENCY_TO_NICE(p->latency_prio);
+
 #ifdef CONFIG_UCLAMP_TASK
 	/*
 	 * This could race with another potential updater, but this is fine
@@ -11027,6 +11063,25 @@ 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 LATENCY_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_LATENCY_NICE || nice > MAX_LATENCY_NICE)
+		return -ERANGE;
+
+	prio = NICE_TO_LATENCY(nice);
+
+	return sched_group_set_latency(css_tg(css), prio);
+}
 #endif
 
 static struct cftype cpu_legacy_files[] = {
@@ -11041,6 +11096,11 @@ 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
 	{
@@ -11258,6 +11318,12 @@ 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..fe9edfa43f65 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -535,9 +535,13 @@ 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 +584,9 @@ 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 +600,25 @@ 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);
@@ -1044,6 +1046,7 @@ 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 84254f52c56a..c40b775452bc 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>
 
@@ -619,13 +620,134 @@ static inline bool entity_before(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)
 
+/*
+ * Compute virtual time from the per-task service numbers:
+ *
+ * Fair schedulers conserve lag: \Sum lag_i = 0
+ *
+ * lag_i = S - s_i = w_i * (V - v_i)
+ *
+ * \Sum lag_i = 0 -> \Sum w_i * (V - v_i) = V * \Sum w_i - \Sum w_i * v_i = 0
+ *
+ * From which we solve V:
+ *
+ *     \Sum v_i * w_i
+ * V = --------------
+ *        \Sum w_i
+ *
+ * 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 - v) + v
+ *
+ *     \Sum ((v_i - v) + v) * w_i   \Sum (v_i - v) * w_i
+ * V = -------------------------- = -------------------- + v
+ *              \Sum w_i                   \Sum w_i
+ *
+ * min_vruntime = v
+ * avg_vruntime = \Sum (v_i - v) * w_i
+ * cfs_rq->load = \Sum w_i
+ *
+ * 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.
+ */
+static void
+avg_vruntime_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 key = entity_key(cfs_rq, se);
+	cfs_rq->avg_vruntime += key * se->load.weight;
+	cfs_rq->avg_load += se->load.weight;
+}
+
+static void
+avg_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 key = entity_key(cfs_rq, se);
+	cfs_rq->avg_vruntime -= key * se->load.weight;
+	cfs_rq->avg_load -= se->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;
+	s64 lag = cfs_rq->avg_vruntime;
+	long load = cfs_rq->avg_load;
+
+	if (curr && curr->on_rq) {
+		lag += entity_key(cfs_rq, curr) * curr->load.weight;
+		load += curr->load.weight;
+	}
+
+	if (load)
+		lag = div_s64(lag, load);
+
+	return cfs_rq->min_vruntime + lag;
+}
+
+/*
+ * Entity is eligible once it received less service than it ought to have,
+ * eg. lag >= 0.
+ *
+ * lag_i = S - s_i = w_i*(V - w_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)
+ */
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	struct sched_entity *curr = cfs_rq->curr;
+	s64 avg_vruntime = cfs_rq->avg_vruntime;
+	long avg_load = cfs_rq->avg_load;
+
+	if (curr && curr->on_rq) {
+		avg_vruntime += entity_key(cfs_rq, curr) * curr->load.weight;
+		avg_load += curr->load.weight;
+	}
+
+	return avg_vruntime >= entity_key(cfs_rq, se) * avg_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)
 {
+	struct sched_entity *se = __pick_first_entity(cfs_rq);
 	struct sched_entity *curr = cfs_rq->curr;
-	struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline);
 
 	u64 vruntime = cfs_rq->min_vruntime;
 
@@ -636,9 +758,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 			curr = NULL;
 	}
 
-	if (leftmost) { /* non-empty tree */
-		struct sched_entity *se = __node_2_se(leftmost);
-
+	if (se) {
 		if (!curr)
 			vruntime = se->vruntime;
 		else
@@ -647,7 +767,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 
 	/* ensure we never gain time by being placed backwards. */
 	u64_u32_store(cfs_rq->min_vruntime,
-		      max_vruntime(cfs_rq->min_vruntime, vruntime));
+		      __update_min_vruntime(cfs_rq, vruntime));
 }
 
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -655,17 +775,51 @@ 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)
@@ -688,6 +842,101 @@ static struct sched_entity *__pick_next_entity(struct sched_entity *se)
 	return __node_2_se(next);
 }
 
+static struct sched_entity *pick_cfs(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+{
+	struct sched_entity *left = __pick_first_entity(cfs_rq);
+
+	/*
+	 * 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;
+
+	return left;
+}
+
+/*
+ * 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 *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+	struct sched_entity *curr = cfs_rq->curr;
+	struct sched_entity *best = 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.
+		 *
+		 * XXX: would it be worth it to do the single division for
+		 *      avg_vruntime() once, instead of the multiplication
+		 *      in entity_eligible() O(log n) times?
+		 */
+		if (!entity_eligible(cfs_rq, se)) {
+			node = node->rb_left;
+			continue;
+		}
+
+		/*
+		 * 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
 struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
@@ -721,6 +970,14 @@ int sched_update_scaling(void)
 }
 #endif
 
+long calc_latency_offset(int prio)
+{
+	u32 weight = sched_prio_to_weight[prio];
+	u64 base = sysctl_sched_min_granularity;
+
+	return div_u64(base << SCHED_FIXEDPOINT_SHIFT, weight);
+}
+
 /*
  * delta /= w
  */
@@ -797,14 +1054,30 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return slice;
 }
 
-/*
- * 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)
+static void set_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	return calc_delta_fair(sched_slice(cfs_rq, se), se);
+	if (sched_feat(EEVDF)) {
+		/*
+		 * For EEVDF the virtual time slope is determined by w_i (iow.
+		 * nice) while the request time r_i is determined by
+		 * latency-nice.
+		 */
+		se->slice = se->latency_offset;
+	} else {
+		/*
+		 * 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.
+		 */
+		se->slice = min_t(u64, sched_slice(cfs_rq, se), sysctl_sched_latency);
+	}
+
+	/*
+	 * vd_i = ve_i + r_i / w_i
+	 */
+	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
+	se->min_deadline = se->deadline;
 }
 
 #include "pelt.h"
@@ -939,6 +1212,13 @@ 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);
+	/*
+	 * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
+	 * this is probably good enough.
+	 */
+	if ((s64)(curr->vruntime - curr->deadline) > 0)
+		set_slice(cfs_rq, curr);
+
 	update_min_vruntime(cfs_rq);
 
 	if (entity_is_task(curr)) {
@@ -3340,6 +3620,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 		/* 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);
@@ -3355,9 +3637,11 @@ 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)
@@ -4669,49 +4953,49 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
-	u64 vruntime = cfs_rq->min_vruntime;
-	u64 sleep_time;
+	u64 vruntime = avg_vruntime(cfs_rq);
 
-	/*
-	 * 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.
-	 */
-	if (initial && sched_feat(START_DEBIT))
-		vruntime += sched_vslice(cfs_rq, se);
+	if (sched_feat(PRESERVE_LAG))
+		vruntime -= se->lag;
 
-	/* sleeps up to a single latency don't count. */
-	if (!initial) {
-		unsigned long thresh;
+	if (sched_feat(FAIR_SLEEPERS)) {
+//		u64 sleep_time;
 
-		if (se_is_idle(se))
-			thresh = sysctl_sched_min_granularity;
-		else
-			thresh = sysctl_sched_latency;
+		/* sleeps up to a single latency don't count. */
+		if (!initial) {
+			unsigned long thresh = TICK_NSEC;
+
+			if (!sched_feat(EEVDF)) {
+				if (se_is_idle(se))
+					thresh = sysctl_sched_min_granularity;
+				else
+					thresh = sysctl_sched_latency;
+			}
+
+			/*
+			 * Halve their sleep time's effect, to allow
+			 * for a gentler effect of sleepers:
+			 */
+			if (sched_feat(GENTLE_FAIR_SLEEPERS))
+				thresh >>= 1;
+
+			vruntime -= calc_delta_fair(thresh, se);
+		}
 
 		/*
-		 * Halve their sleep time's effect, to allow
-		 * for a gentler effect of sleepers:
+		 * Pull vruntime of the entity being placed to the base level of
+		 * cfs_rq, to prevent boosting it if placed backwards.  If the entity
+		 * slept for a long time, don't even try to compare its vruntime with
+		 * the base as it may be too far off and the comparison may get
+		 * inversed due to s64 overflow.
+		sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
+		if ((s64)sleep_time < 60LL * NSEC_PER_SEC)
 		 */
-		if (sched_feat(GENTLE_FAIR_SLEEPERS))
-			thresh >>= 1;
-
-		vruntime -= thresh;
+			vruntime = max_vruntime(se->vruntime, vruntime);
 	}
 
-	/*
-	 * Pull vruntime of the entity being placed to the base level of
-	 * cfs_rq, to prevent boosting it if placed backwards.  If the entity
-	 * slept for a long time, don't even try to compare its vruntime with
-	 * the base as it may be too far off and the comparison may get
-	 * inversed due to s64 overflow.
-	 */
-	sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
-	if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
-		se->vruntime = vruntime;
-	else
-		se->vruntime = max_vruntime(se->vruntime, vruntime);
+	se->vruntime = vruntime;
+	set_slice(cfs_rq, se);
 }
 
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -4879,6 +5163,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	clear_buddies(cfs_rq, se);
 
+	if (sched_feat(PRESERVE_LAG) && (flags & DEQUEUE_SLEEP))
+		se->lag = avg_vruntime(cfs_rq) - se->vruntime;
+
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	se->on_rq = 0;
@@ -4917,19 +5204,20 @@ 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;
+	unsigned long 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);
+	if (sched_feat(EEVDF)) {
+		if (pick_eevdf(cfs_rq) != curr)
+			goto preempt;
+
+		return;
+	}
 
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-	if (delta_exec > ideal_runtime) {
+	if (delta_exec > curr->slice) {
+preempt:
 		resched_curr(rq_of(cfs_rq));
 		/*
 		 * The current task ran long enough, ensure it doesn't get
@@ -4953,7 +5241,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	if (delta < 0)
 		return;
 
-	if (delta > ideal_runtime)
+	if (delta > curr->slice)
 		resched_curr(rq_of(cfs_rq));
 }
 
@@ -5008,17 +5296,20 @@ 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;
+	struct sched_entity *left, *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;
+	if (sched_feat(EEVDF)) {
+		/*
+		 * Enabling NEXT_BUDDY will affect latency but not fairness.
+		 */
+		if (sched_feat(NEXT_BUDDY) &&
+		    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
+			return cfs_rq->next;
 
-	se = left; /* ideally we run the leftmost entity */
+		return pick_eevdf(cfs_rq);
+	}
+
+	se = left = pick_cfs(cfs_rq, curr);
 
 	/*
 	 * Avoid running the skip buddy, if running something else can
@@ -6113,13 +6404,12 @@ 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) {
@@ -7891,7 +8181,19 @@ 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));
+	cfs_rq = cfs_rq_of(se);
+	update_curr(cfs_rq);
+
+	if (sched_feat(EEVDF)) {
+		/*
+		 * XXX pick_eevdf(cfs_rq) != se ?
+		 */
+		if (pick_eevdf(cfs_rq) == pse)
+			goto preempt;
+
+		return;
+	}
+
 	if (wakeup_preempt_entity(se, pse) == 1) {
 		/*
 		 * Bias pick_next to pick the sched entity that is
@@ -8137,7 +8439,7 @@ static void yield_task_fair(struct rq *rq)
 
 	clear_buddies(cfs_rq, se);
 
-	if (curr->policy != SCHED_BATCH) {
+	if (sched_feat(EEVDF) || curr->policy != SCHED_BATCH) {
 		update_rq_clock(rq);
 		/*
 		 * Update run-time statistics of the 'current'.
@@ -8150,6 +8452,8 @@ static void yield_task_fair(struct rq *rq)
 		 */
 		rq_clock_skip_update(rq);
 	}
+	if (sched_feat(EEVDF))
+		se->deadline += calc_delta_fair(se->slice, se);
 
 	set_skip_buddy(se);
 }
@@ -11902,8 +12206,8 @@ 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);
 }
@@ -12330,6 +12634,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		goto err;
 
 	tg->shares = NICE_0_LOAD;
+	tg->latency_prio = DEFAULT_LATENCY_PRIO;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
 
@@ -12428,6 +12733,9 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 	}
 
 	se->my_q = cfs_rq;
+
+	se->latency_offset = calc_latency_offset(tg->latency_prio);
+
 	/* guarantee group entities always have weight */
 	update_load_set(&se->load, NICE_0_LOAD);
 	se->parent = parent;
@@ -12558,6 +12866,34 @@ int sched_group_set_idle(struct task_group *tg, long idle)
 	return 0;
 }
 
+int sched_group_set_latency(struct task_group *tg, int prio)
+{
+	long latency_offset;
+	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;
+	latency_offset = calc_latency_offset(prio);
+
+	for_each_possible_cpu(i) {
+		struct sched_entity *se = tg->se[i];
+
+		WRITE_ONCE(se->latency_offset, latency_offset);
+	}
+
+	mutex_unlock(&shares_mutex);
+	return 0;
+}
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
 
 void free_fair_sched_group(struct task_group *tg) { }
@@ -12584,7 +12920,7 @@ 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..49c7e6fa4c71 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,16 +1,18 @@
 /* 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(FAIR_SLEEPERS, false)
 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.
  */
-SCHED_FEAT(START_DEBIT, true)
+SCHED_FEAT(PRESERVE_LAG, true)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
@@ -102,3 +104,5 @@ SCHED_FEAT(LATENCY_WARN, false)
 
 SCHED_FEAT(ALT_PERIOD, true)
 SCHED_FEAT(BASE_SLICE, true)
+
+SCHED_FEAT(EEVDF, true)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9e8bb6278604..fe5af7aaa931 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 +558,9 @@ struct cfs_rq {
 	unsigned int		idle_nr_running;   /* SCHED_IDLE */
 	unsigned int		idle_h_nr_running; /* SCHED_IDLE */
 
+	s64			avg_vruntime;
+	u64			avg_load;
+
 	u64			exec_clock;
 	u64			min_vruntime;
 #ifdef CONFIG_SCHED_CORE
@@ -2478,6 +2485,8 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 extern unsigned int sysctl_numa_balancing_hot_threshold;
 #endif
 
+extern long calc_latency_offset(int prio);
+
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -3251,4 +3260,7 @@ static inline void update_current_exec_runtime(struct task_struct *curr,
 	cgroup_account_cputime(curr, delta_exec);
 }
 
+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.rc2