File _service:download_files:0001-bore-6.3-introduce... of Package linux-px

Overview Repositories Revisions Requests Users Attributes Meta

File _service:download_files:0001-bore-6.3-introduce-BORE-Scheduler-with-EEVDF-patches.patch of Package linux-px (Revision 41496267b0e9ba6e75fd24ffbbfd5e00)

Currently displaying revision 41496267b0e9ba6e75fd24ffbbfd5e00 , Show latest

From 31413577883ed0996c8dfb642631facfc8719a0d Mon Sep 17 00:00:00 2001
From: Piotr Gorski <lucjan.lucjanov@gmail.com>
Date: Sat, 6 May 2023 14:09:22 +0200
Subject: [PATCH] bore-6.3: introduce BORE Scheduler with EEVDF patches

diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst
index 5e40b3f43..df6062eb3 100644
--- a/Documentation/accounting/psi.rst
+++ b/Documentation/accounting/psi.rst
@@ -105,6 +105,10 @@ prevent overly frequent polling. Max limit is chosen as a high enough number
 after which monitors are most likely not needed and psi averages can be used
 instead.
 
+Unprivileged users can also create monitors, with the only limitation that the
+window size must be a multiple of 2s, in order to prevent excessive resource
+usage.
+
 When activated, psi monitor stays active for at least the duration of one
 tracking window to avoid repeated activations/deactivations when system is
 bouncing in and out of the stall state.
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index f67c08293..a39dfda3d 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/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 9ff480e94..6510883c5 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -174,32 +174,19 @@ int arch_asym_cpu_priority(int cpu)
 
 /**
  * sched_set_itmt_core_prio() - Set CPU priority based on ITMT
- * @prio:	Priority of cpu core
- * @core_cpu:	The cpu number associated with the core
+ * @prio:	Priority of @cpu
+ * @cpu:	The CPU number
  *
  * The pstate driver will find out the max boost frequency
  * and call this function to set a priority proportional
- * to the max boost frequency. CPU with higher boost
+ * to the max boost frequency. CPUs with higher boost
  * frequency will receive higher priority.
  *
  * No need to rebuild sched domain after updating
  * the CPU priorities. The sched domains have no
  * dependency on CPU priorities.
  */
-void sched_set_itmt_core_prio(int prio, int core_cpu)
+void sched_set_itmt_core_prio(int prio, int cpu)
 {
-	int cpu, i = 1;
-
-	for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) {
-		int smt_prio;
-
-		/*
-		 * Ensure that the siblings are moved to the end
-		 * of the priority chain and only used when
-		 * all other high priority cpus are out of capacity.
-		 */
-		smt_prio = prio * smp_num_siblings / (i * i);
-		per_cpu(sched_core_priority, cpu) = smt_prio;
-		i++;
-	}
+	per_cpu(sched_core_priority, cpu) = prio;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9013bb282..cea297d97 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -547,7 +547,7 @@ static int x86_core_flags(void)
 #ifdef CONFIG_SCHED_SMT
 static int x86_smt_flags(void)
 {
-	return cpu_smt_flags() | x86_sched_itmt_flags();
+	return cpu_smt_flags();
 }
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
@@ -578,7 +578,7 @@ static struct sched_domain_topology_level x86_hybrid_topology[] = {
 #ifdef CONFIG_SCHED_MC
 	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(DIE) },
 	{ NULL, },
 };
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f11bdbe4c..822fbdb54 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -363,8 +363,7 @@ static int vhost_worker(void *data)
 			kcov_remote_start_common(dev->kcov_handle);
 			work->fn(work);
 			kcov_remote_stop();
-			if (need_resched())
-				schedule();
+			cond_resched();
 		}
 	}
 	kthread_unuse_mm(dev->mm);
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 293e29960..9b9b38e89 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -13,6 +13,7 @@
 #include <linux/ftrace.h>
 #include <linux/completion.h>
 #include <linux/list.h>
+#include <linux/livepatch_sched.h>
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 
diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h
new file mode 100644
index 000000000..013794fb5
--- /dev/null
+++ b/include/linux/livepatch_sched.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_LIVEPATCH_SCHED_H_
+#define _LINUX_LIVEPATCH_SCHED_H_
+
+#include <linux/jump_label.h>
+#include <linux/static_call_types.h>
+
+#ifdef CONFIG_LIVEPATCH
+
+void __klp_sched_try_switch(void);
+
+#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+
+DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
+
+static __always_inline void klp_sched_try_switch(void)
+{
+	if (static_branch_unlikely(&klp_sched_try_switch_key))
+		__klp_sched_try_switch();
+}
+
+#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
+#else /* !CONFIG_LIVEPATCH */
+static inline void klp_sched_try_switch(void) {}
+static inline void __klp_sched_try_switch(void) {}
+#endif /* CONFIG_LIVEPATCH */
+
+#endif /* _LINUX_LIVEPATCH_SCHED_H_ */
diff --git a/include/linux/psi.h b/include/linux/psi.h
index b029a847d..ab26200c2 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res);
+			char *buf, enum psi_res res, struct file *file);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 1e0a0d7ac..040c08958 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -151,6 +151,9 @@ struct psi_trigger {
 
 	/* Deferred event(s) from previous ratelimit window */
 	bool pending_event;
+
+	/* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */
+	enum psi_aggregators aggregator;
 };
 
 struct psi_group {
@@ -171,30 +174,34 @@ struct psi_group {
 	/* Aggregator work control */
 	struct delayed_work avgs_work;
 
+	/* Unprivileged triggers against N*PSI_FREQ windows */
+	struct list_head avg_triggers;
+	u32 avg_nr_triggers[NR_PSI_STATES - 1];
+
 	/* Total stall times and sampled pressure averages */
 	u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1];
 	unsigned long avg[NR_PSI_STATES - 1][3];
 
-	/* Monitor work control */
-	struct task_struct __rcu *poll_task;
-	struct timer_list poll_timer;
-	wait_queue_head_t poll_wait;
-	atomic_t poll_wakeup;
-	atomic_t poll_scheduled;
+	/* Monitor RT polling work control */
+	struct task_struct __rcu *rtpoll_task;
+	struct timer_list rtpoll_timer;
+	wait_queue_head_t rtpoll_wait;
+	atomic_t rtpoll_wakeup;
+	atomic_t rtpoll_scheduled;
 
 	/* Protects data used by the monitor */
-	struct mutex trigger_lock;
-
-	/* Configured polling triggers */
-	struct list_head triggers;
-	u32 nr_triggers[NR_PSI_STATES - 1];
-	u32 poll_states;
-	u64 poll_min_period;
-
-	/* Total stall times at the start of monitor activation */
-	u64 polling_total[NR_PSI_STATES - 1];
-	u64 polling_next_update;
-	u64 polling_until;
+	struct mutex rtpoll_trigger_lock;
+
+	/* Configured RT polling triggers */
+	struct list_head rtpoll_triggers;
+	u32 rtpoll_nr_triggers[NR_PSI_STATES - 1];
+	u32 rtpoll_states;
+	u64 rtpoll_min_period;
+
+	/* Total stall times at the start of RT polling monitor activation */
+	u64 rtpoll_total[NR_PSI_STATES - 1];
+	u64 rtpoll_next_update;
+	u64 rtpoll_until;
 };
 
 #else /* CONFIG_PSI */
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index d1c53e9d8..a78e692a9 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 63d242164..8adf461cb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -36,6 +36,7 @@
 #include <linux/seqlock.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
+#include <linux/livepatch_sched.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -548,13 +549,24 @@ 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;
 
 	u64				exec_start;
 	u64				sum_exec_runtime;
-	u64				vruntime;
 	u64				prev_sum_exec_runtime;
+	u64				vruntime;
+#ifdef CONFIG_SCHED_BORE
+	u64				prev_burst_time;
+	u64				burst_time;
+	u64				max_burst_time;
+	u8				penalty_score;
+#endif // CONFIG_SCHED_BORE
+	s64				vlag;
+	u64				slice;
 
 	u64				nr_migrations;
 
@@ -784,6 +796,7 @@ 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;
@@ -983,6 +996,10 @@ struct task_struct {
 	struct list_head		children;
 	struct list_head		sibling;
 	struct task_struct		*group_leader;
+#ifdef CONFIG_SCHED_BORE
+	u64	child_burst_cache;
+	u64	child_burst_last_cached;
+#endif // CONFIG_SCHED_BORE
 
 	/*
 	 * 'ptraced' is the list of tasks this task is using ptrace() on.
@@ -2070,6 +2087,9 @@ extern int __cond_resched(void);
 
 #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
+void sched_dynamic_klp_enable(void);
+void sched_dynamic_klp_disable(void);
+
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
 static __always_inline int _cond_resched(void)
@@ -2078,6 +2098,7 @@ static __always_inline int _cond_resched(void)
 }
 
 #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+
 extern int dynamic_cond_resched(void);
 
 static __always_inline int _cond_resched(void)
@@ -2085,20 +2106,25 @@ static __always_inline int _cond_resched(void)
 	return dynamic_cond_resched();
 }
 
-#else
+#else /* !CONFIG_PREEMPTION */
 
 static inline int _cond_resched(void)
 {
+	klp_sched_try_switch();
 	return __cond_resched();
 }
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
-#else
+#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */
 
-static inline int _cond_resched(void) { return 0; }
+static inline int _cond_resched(void)
+{
+	klp_sched_try_switch();
+	return 0;
+}
 
-#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */
+#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */
 
 #define cond_resched() ({			\
 	__might_resched(__FILE__, __LINE__, 0);	\
diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index 57bde66d9..fad77b517 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -132,12 +132,9 @@ SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
 /*
  * Place busy tasks earlier in the domain
  *
- * SHARED_CHILD: Usually set on the SMT level. Technically could be set further
- *               up, but currently assumed to be set from the base domain
- *               upwards (see update_top_cache_domain()).
  * NEEDS_GROUPS: Load balancing flag.
  */
-SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS)
+SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
 
 /*
  * Prefer to place tasks in a sibling domain
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ce..b2e932c25 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 f2c4589d4..db1e8199e 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/Kconfig b/init/Kconfig
index c88bb30a8..ab07f7c8e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1281,6 +1281,26 @@ config CHECKPOINT_RESTORE
 
 	  If unsure, say N here.
 
+config SCHED_BORE
+	bool "Burst-Oriented Response Enhancer"
+	default y
+	help
+	  In Desktop and Mobile computing, one might prefer interactive
+	  tasks to keep responsive no matter what they run in the background.
+
+	  Enabling this kernel feature modifies the scheduler to discriminate
+	  tasks by their burst time (runtime since it last went sleeping or
+	  yielding state) and prioritize those that run less bursty.
+	  Such tasks usually include window compositor, widgets backend,
+	  terminal emulator, video playback, games and so on.
+	  With a little impact to scheduling fairness, it may improve
+	  responsiveness especially under heavy background workload.
+
+	  You can turn it off by setting the sysctl kernel.sched_bore = 0.
+	  Enabling this feature implies NO_GENTLE_FAIR_SLEEPERS by default.
+
+	  If unsure say Y here.
+
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
 	select CGROUPS
diff --git a/init/init_task.c b/init/init_task.c
index ff6c4b9bf..511cbcf35 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/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 935e8121b..e6ab2e405 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3761,7 +3761,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf,
 	}
 
 	psi = cgroup_psi(cgrp);
-	new = psi_trigger_create(psi, buf, res);
+	new = psi_trigger_create(psi, buf, res, of->file);
 	if (IS_ERR(new)) {
 		cgroup_put(cgrp);
 		return PTR_ERR(new);
@@ -3867,6 +3867,14 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of,
 	return psi_trigger_poll(&ctx->psi.trigger, of->file, pt);
 }
 
+static int cgroup_pressure_open(struct kernfs_open_file *of)
+{
+	if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+
+	return 0;
+}
+
 static void cgroup_pressure_release(struct kernfs_open_file *of)
 {
 	struct cgroup_file_ctx *ctx = of->priv;
@@ -5266,6 +5274,7 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "io.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IO]),
+		.open = cgroup_pressure_open,
 		.seq_show = cgroup_io_pressure_show,
 		.write = cgroup_io_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5274,6 +5283,7 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "memory.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]),
+		.open = cgroup_pressure_open,
 		.seq_show = cgroup_memory_pressure_show,
 		.write = cgroup_memory_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5282,6 +5292,7 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "cpu.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]),
+		.open = cgroup_pressure_open,
 		.seq_show = cgroup_cpu_pressure_show,
 		.write = cgroup_cpu_pressure_write,
 		.poll = cgroup_pressure_poll,
@@ -5291,6 +5302,7 @@ static struct cftype cgroup_psi_files[] = {
 	{
 		.name = "irq.pressure",
 		.file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]),
+		.open = cgroup_pressure_open,
 		.seq_show = cgroup_irq_pressure_show,
 		.write = cgroup_irq_pressure_write,
 		.poll = cgroup_pressure_poll,
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 4bd2d5e10..eea7c8ec6 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -33,6 +33,7 @@
  *
  * - klp_ftrace_handler()
  * - klp_update_patch_state()
+ * - __klp_sched_try_switch()
  */
 DEFINE_MUTEX(klp_mutex);
 
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index f1b25ec58..e9fd83a02 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -9,11 +9,14 @@
 
 #include <linux/cpu.h>
 #include <linux/stacktrace.h>
+#include <linux/static_call.h>
 #include "core.h"
 #include "patch.h"
 #include "transition.h"
 
 #define MAX_STACK_ENTRIES  100
+DEFINE_PER_CPU(unsigned long[MAX_STACK_ENTRIES], klp_stack_entries);
+
 #define STACK_ERR_BUF_SIZE 128
 
 #define SIGNALS_TIMEOUT 15
@@ -24,6 +27,25 @@ static int klp_target_state = KLP_UNDEFINED;
 
 static unsigned int klp_signals_cnt;
 
+/*
+ * When a livepatch is in progress, enable klp stack checking in
+ * cond_resched().  This helps CPU-bound kthreads get patched.
+ */
+#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+
+#define klp_cond_resched_enable() sched_dynamic_klp_enable()
+#define klp_cond_resched_disable() sched_dynamic_klp_disable()
+
+#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
+DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
+EXPORT_SYMBOL(klp_sched_try_switch_key);
+
+#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
+
+#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
 /*
  * This work can be performed periodically to finish patching or unpatching any
  * "straggler" tasks which failed to transition in the first attempt.
@@ -172,8 +194,8 @@ void klp_update_patch_state(struct task_struct *task)
 	 * barrier (smp_rmb) for two cases:
 	 *
 	 * 1) Enforce the order of the TIF_PATCH_PENDING read and the
-	 *    klp_target_state read.  The corresponding write barrier is in
-	 *    klp_init_transition().
+	 *    klp_target_state read.  The corresponding write barriers are in
+	 *    klp_init_transition() and klp_reverse_transition().
 	 *
 	 * 2) Enforce the order of the TIF_PATCH_PENDING read and a future read
 	 *    of func->transition, if klp_ftrace_handler() is called later on
@@ -240,12 +262,15 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
  */
 static int klp_check_stack(struct task_struct *task, const char **oldname)
 {
-	static unsigned long entries[MAX_STACK_ENTRIES];
+	unsigned long *entries = this_cpu_ptr(klp_stack_entries);
 	struct klp_object *obj;
 	struct klp_func *func;
 	int ret, nr_entries;
 
-	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
+	/* Protect 'klp_stack_entries' */
+	lockdep_assert_preemption_disabled();
+
+	ret = stack_trace_save_tsk_reliable(task, entries, MAX_STACK_ENTRIES);
 	if (ret < 0)
 		return -EINVAL;
 	nr_entries = ret;
@@ -307,7 +332,11 @@ static bool klp_try_switch_task(struct task_struct *task)
 	 * functions.  If all goes well, switch the task to the target patch
 	 * state.
 	 */
-	ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+	if (task == current)
+		ret = klp_check_and_switch_task(current, &old_name);
+	else
+		ret = task_call_func(task, klp_check_and_switch_task, &old_name);
+
 	switch (ret) {
 	case 0:		/* success */
 		break;
@@ -334,6 +363,44 @@ static bool klp_try_switch_task(struct task_struct *task)
 	return !ret;
 }
 
+void __klp_sched_try_switch(void)
+{
+	if (likely(!klp_patch_pending(current)))
+		return;
+
+	/*
+	 * This function is called from cond_resched() which is called in many
+	 * places throughout the kernel.  Using the klp_mutex here might
+	 * deadlock.
+	 *
+	 * Instead, disable preemption to prevent racing with other callers of
+	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
+	 * able to switch this task while it's running.
+	 */
+	preempt_disable();
+
+	/*
+	 * Make sure current didn't get patched between the above check and
+	 * preempt_disable().
+	 */
+	if (unlikely(!klp_patch_pending(current)))
+		goto out;
+
+	/*
+	 * Enforce the order of the TIF_PATCH_PENDING read above and the
+	 * klp_target_state read in klp_try_switch_task().  The corresponding
+	 * write barriers are in klp_init_transition() and
+	 * klp_reverse_transition().
+	 */
+	smp_rmb();
+
+	klp_try_switch_task(current);
+
+out:
+	preempt_enable();
+}
+EXPORT_SYMBOL(__klp_sched_try_switch);
+
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
  * Kthreads with TIF_PATCH_PENDING set are woken up.
@@ -440,7 +507,8 @@ void klp_try_complete_transition(void)
 		return;
 	}
 
-	/* we're done, now cleanup the data structures */
+	/* Done!  Now cleanup the data structures. */
+	klp_cond_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -492,6 +560,8 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
+	klp_cond_resched_enable();
+
 	klp_signals_cnt = 0;
 }
 
@@ -547,8 +617,9 @@ void klp_init_transition(struct klp_patch *patch, int state)
 	 * see a func in transition with a task->patch_state of KLP_UNDEFINED.
 	 *
 	 * Also enforce the order of the klp_target_state write and future
-	 * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() doesn't
-	 * set a task->patch_state to KLP_UNDEFINED.
+	 * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() and
+	 * __klp_sched_try_switch() don't set a task->patch_state to
+	 * KLP_UNDEFINED.
 	 */
 	smp_wmb();
 
@@ -584,14 +655,10 @@ void klp_reverse_transition(void)
 		 klp_target_state == KLP_PATCHED ? "patching to unpatching" :
 						   "unpatching to patching");
 
-	klp_transition_patch->enabled = !klp_transition_patch->enabled;
-
-	klp_target_state = !klp_target_state;
-
 	/*
 	 * Clear all TIF_PATCH_PENDING flags to prevent races caused by
-	 * klp_update_patch_state() running in parallel with
-	 * klp_start_transition().
+	 * klp_update_patch_state() or __klp_sched_try_switch() running in
+	 * parallel with the reverse transition.
 	 */
 	read_lock(&tasklist_lock);
 	for_each_process_thread(g, task)
@@ -601,9 +668,28 @@ void klp_reverse_transition(void)
 	for_each_possible_cpu(cpu)
 		clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING);
 
-	/* Let any remaining calls to klp_update_patch_state() complete */
+	/*
+	 * Make sure all existing invocations of klp_update_patch_state() and
+	 * __klp_sched_try_switch() see the cleared TIF_PATCH_PENDING before
+	 * starting the reverse transition.
+	 */
 	klp_synchronize_transition();
 
+	/*
+	 * All patching has stopped, now re-initialize the global variables to
+	 * prepare for the reverse transition.
+	 */
+	klp_transition_patch->enabled = !klp_transition_patch->enabled;
+	klp_target_state = !klp_target_state;
+
+	/*
+	 * Enforce the order of the klp_target_state write and the
+	 * TIF_PATCH_PENDING writes in klp_start_transition() to ensure
+	 * klp_update_patch_state() and __klp_sched_try_switch() don't set
+	 * task->patch_state to the wrong value.
+	 */
+	smp_wmb();
+
 	klp_start_transition();
 }
 
@@ -617,9 +703,9 @@ void klp_copy_process(struct task_struct *child)
 	 * the task flag up to date with the parent here.
 	 *
 	 * The operation is serialized against all klp_*_transition()
-	 * operations by the tasklist_lock. The only exception is
-	 * klp_update_patch_state(current), but we cannot race with
-	 * that because we are current.
+	 * operations by the tasklist_lock. The only exceptions are
+	 * klp_update_patch_state(current) and __klp_sched_try_switch(), but we
+	 * cannot race with them because we are current.
 	 */
 	if (test_tsk_thread_flag(current, TIF_PATCH_PENDING))
 		set_tsk_thread_flag(child, TIF_PATCH_PENDING);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 5732fa75e..b5cc2b534 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -300,6 +300,9 @@ noinstr u64 local_clock(void)
 	if (static_branch_likely(&__sched_clock_stable))
 		return sched_clock() + __sched_clock_offset;
 
+	if (!static_branch_likely(&sched_clock_running))
+		return sched_clock();
+
 	preempt_disable_notrace();
 	clock = sched_clock_local(this_scd());
 	preempt_enable_notrace();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0d18c3969..ca51a2556 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -261,36 +261,51 @@ void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags)
 		resched_curr(rq);
 }
 
-/*
- * Find left-most (aka, highest priority) task matching @cookie.
- */
-static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
+static int sched_task_is_throttled(struct task_struct *p, int cpu)
 {
-	struct rb_node *node;
-
-	node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp);
-	/*
-	 * The idle task always matches any cookie!
-	 */
-	if (!node)
-		return idle_sched_class.pick_task(rq);
+	if (p->sched_class->task_is_throttled)
+		return p->sched_class->task_is_throttled(p, cpu);
 
-	return __node_2_sc(node);
+	return 0;
 }
 
 static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie)
 {
 	struct rb_node *node = &p->core_node;
+	int cpu = task_cpu(p);
+
+	do {
+		node = rb_next(node);
+		if (!node)
+			return NULL;
+
+		p = __node_2_sc(node);
+		if (p->core_cookie != cookie)
+			return NULL;
+
+	} while (sched_task_is_throttled(p, cpu));
 
-	node = rb_next(node);
+	return p;
+}
+
+/*
+ * Find left-most (aka, highest priority) and unthrottled task matching @cookie.
+ * If no suitable task is found, NULL will be returned.
+ */
+static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie)
+{
+	struct task_struct *p;
+	struct rb_node *node;
+
+	node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp);
 	if (!node)
 		return NULL;
 
-	p = container_of(node, struct task_struct, core_node);
-	if (p->core_cookie != cookie)
-		return NULL;
+	p = __node_2_sc(node);
+	if (!sched_task_is_throttled(p, rq->cpu))
+		return p;
 
-	return p;
+	return sched_core_next(p, cookie);
 }
 
 /*
@@ -1285,6 +1300,12 @@ 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
@@ -4418,6 +4439,37 @@ int wake_up_state(struct task_struct *p, unsigned int state)
 	return try_to_wake_up(p, state, 0);
 }
 
+#ifdef CONFIG_SCHED_BORE
+extern unsigned int sched_burst_cache_lifetime;
+
+static inline void update_burst_cache(struct task_struct *p) {
+	u32 cnt = 0;
+	u64 sum = 0, avg = 0;
+	struct task_struct *child;
+	list_for_each_entry(child, &p->children, sibling) {
+		cnt++;
+		sum += child->se.max_burst_time >> 8;
+	}
+	if (cnt) avg = div_u64(sum, cnt) << 8;
+	p->child_burst_cache = max(avg, p->se.max_burst_time);
+}
+
+static void adjust_prev_burst(struct task_struct *p) {
+	struct task_struct *parent = p->parent;
+	u64 ktime = ktime_to_ns(ktime_get());
+
+	if (likely(parent)) {
+		if (parent->child_burst_last_cached + sched_burst_cache_lifetime < ktime) {
+			parent->child_burst_last_cached = ktime;
+			update_burst_cache(parent);
+		}
+		if (p->se.prev_burst_time < parent->child_burst_cache)
+			p->se.prev_burst_time = parent->child_burst_cache;
+	}
+	p->se.max_burst_time = p->se.prev_burst_time;
+} 
+#endif // CONFIG_SCHED_BORE
+
 /*
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
@@ -4434,8 +4486,14 @@ 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;
+#ifdef CONFIG_SCHED_BORE
+	p->se.burst_time      = 0;
+#endif // CONFIG_SCHED_BORE
+	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
@@ -4659,6 +4717,9 @@ late_initcall(sched_core_sysctl_init);
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	__sched_fork(clone_flags, p);
+#ifdef CONFIG_SCHED_BORE
+	adjust_prev_burst(p);
+#endif // CONFIG_SCHED_BORE
 	/*
 	 * We mark the process as NEW here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
@@ -4686,6 +4747,7 @@ 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
@@ -6239,7 +6301,7 @@ static bool try_steal_cookie(int this, int that)
 		goto unlock;
 
 	p = sched_core_find(src, cookie);
-	if (p == src->idle)
+	if (!p)
 		goto unlock;
 
 	do {
@@ -6251,6 +6313,13 @@ static bool try_steal_cookie(int this, int that)
 
 		if (p->core_occupation > dst->idle->core_occupation)
 			goto next;
+		/*
+		 * sched_core_find() and sched_core_next() will ensure that task @p
+		 * is not throttled now, we also need to check whether the runqueue
+		 * of the destination CPU is being throttled.
+		 */
+		if (sched_task_is_throttled(p, this))
+			goto next;
 
 		deactivate_task(src, p, 0);
 		set_task_cpu(p, this);
@@ -7431,7 +7500,7 @@ 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;
 
@@ -7455,6 +7524,13 @@ 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:
  */
@@ -7595,6 +7671,13 @@ 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();
 
@@ -7629,6 +7712,9 @@ 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;
@@ -7717,6 +7803,7 @@ 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) {
@@ -7927,6 +8014,9 @@ 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?
@@ -8164,6 +8254,8 @@ 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
@@ -8506,6 +8598,7 @@ EXPORT_STATIC_CALL_TRAMP(might_resched);
 static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
 int __sched dynamic_cond_resched(void)
 {
+	klp_sched_try_switch();
 	if (!static_branch_unlikely(&sk_dynamic_cond_resched))
 		return 0;
 	return __cond_resched();
@@ -8654,13 +8747,17 @@ int sched_dynamic_mode(const char *str)
 #error "Unsupported PREEMPT_DYNAMIC mechanism"
 #endif
 
-void sched_dynamic_update(int mode)
+static DEFINE_MUTEX(sched_dynamic_mutex);
+static bool klp_override;
+
+static void __sched_dynamic_update(int mode)
 {
 	/*
 	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
 	 * the ZERO state, which is invalid.
 	 */
-	preempt_dynamic_enable(cond_resched);
+	if (!klp_override)
+		preempt_dynamic_enable(cond_resched);
 	preempt_dynamic_enable(might_resched);
 	preempt_dynamic_enable(preempt_schedule);
 	preempt_dynamic_enable(preempt_schedule_notrace);
@@ -8668,36 +8765,79 @@ void sched_dynamic_update(int mode)
 
 	switch (mode) {
 	case preempt_dynamic_none:
-		preempt_dynamic_enable(cond_resched);
+		if (!klp_override)
+			preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
 		preempt_dynamic_disable(preempt_schedule_notrace);
 		preempt_dynamic_disable(irqentry_exit_cond_resched);
-		pr_info("Dynamic Preempt: none\n");
+		if (mode != preempt_dynamic_mode)
+			pr_info("Dynamic Preempt: none\n");
 		break;
 
 	case preempt_dynamic_voluntary:
-		preempt_dynamic_enable(cond_resched);
+		if (!klp_override)
+			preempt_dynamic_enable(cond_resched);
 		preempt_dynamic_enable(might_resched);
 		preempt_dynamic_disable(preempt_schedule);
 		preempt_dynamic_disable(preempt_schedule_notrace);
 		preempt_dynamic_disable(irqentry_exit_cond_resched);
-		pr_info("Dynamic Preempt: voluntary\n");
+		if (mode != preempt_dynamic_mode)
+			pr_info("Dynamic Preempt: voluntary\n");
 		break;
 
 	case preempt_dynamic_full:
-		preempt_dynamic_disable(cond_resched);
+		if (!klp_override)
+			preempt_dynamic_disable(cond_resched);
 		preempt_dynamic_disable(might_resched);
 		preempt_dynamic_enable(preempt_schedule);
 		preempt_dynamic_enable(preempt_schedule_notrace);
 		preempt_dynamic_enable(irqentry_exit_cond_resched);
-		pr_info("Dynamic Preempt: full\n");
+		if (mode != preempt_dynamic_mode)
+			pr_info("Dynamic Preempt: full\n");
 		break;
 	}
 
 	preempt_dynamic_mode = mode;
 }
 
+void sched_dynamic_update(int mode)
+{
+	mutex_lock(&sched_dynamic_mutex);
+	__sched_dynamic_update(mode);
+	mutex_unlock(&sched_dynamic_mutex);
+}
+
+#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
+
+static int klp_cond_resched(void)
+{
+	__klp_sched_try_switch();
+	return __cond_resched();
+}
+
+void sched_dynamic_klp_enable(void)
+{
+	mutex_lock(&sched_dynamic_mutex);
+
+	klp_override = true;
+	static_call_update(cond_resched, klp_cond_resched);
+
+	mutex_unlock(&sched_dynamic_mutex);
+}
+
+void sched_dynamic_klp_disable(void)
+{
+	mutex_lock(&sched_dynamic_mutex);
+
+	klp_override = false;
+	__sched_dynamic_update(preempt_dynamic_mode);
+
+	mutex_unlock(&sched_dynamic_mutex);
+}
+
+#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+
 static int __init setup_preempt_mode(char *str)
 {
 	int mode = sched_dynamic_mode(str);
@@ -9126,6 +9266,10 @@ void __init init_idle(struct task_struct *idle, int cpu)
 
 	idle->__state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
+#ifdef CONFIG_SCHED_BORE
+	idle->se.prev_burst_time = 0;
+	idle->se.max_burst_time = 0;
+#endif //CONFIG_SCHED_BORE
 	/*
 	 * PF_KTHREAD should already be set at this point; regardless, make it
 	 * look like a proper per-CPU kthread.
@@ -9793,6 +9937,10 @@ void __init sched_init(void)
 	BUG_ON(&dl_sched_class != &stop_sched_class + 1);
 #endif
 
+#ifdef CONFIG_SCHED_BORE
+	printk(KERN_INFO "BORE (Burst-Oriented Response Enhancer) CPU Scheduler modification 2.2.3 by Masahito Suzuki");
+#endif // CONFIG_SCHED_BORE
+
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -10332,7 +10480,7 @@ void sched_release_group(struct task_group *tg)
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-static void sched_change_group(struct task_struct *tsk)
+static struct task_group *sched_get_task_group(struct task_struct *tsk)
 {
 	struct task_group *tg;
 
@@ -10344,7 +10492,13 @@ static void sched_change_group(struct task_struct *tsk)
 	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
-	tsk->sched_task_group = tg;
+
+	return tg;
+}
+
+static void sched_change_group(struct task_struct *tsk, struct task_group *group)
+{
+	tsk->sched_task_group = group;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_change_group)
@@ -10365,10 +10519,19 @@ void sched_move_task(struct task_struct *tsk)
 {
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
+	struct task_group *group;
 	struct rq_flags rf;
 	struct rq *rq;
 
 	rq = task_rq_lock(tsk, &rf);
+	/*
+	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
+	 * group changes.
+	 */
+	group = sched_get_task_group(tsk);
+	if (group == tsk->sched_task_group)
+		goto unlock;
+
 	update_rq_clock(rq);
 
 	running = task_current(rq, tsk);
@@ -10379,7 +10542,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (running)
 		put_prev_task(rq, tsk);
 
-	sched_change_group(tsk);
+	sched_change_group(tsk, group);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
@@ -10393,6 +10556,7 @@ void sched_move_task(struct task_struct *tsk)
 		resched_curr(rq);
 	}
 
+unlock:
 	task_rq_unlock(rq, tsk, &rf);
 }
 
@@ -11036,6 +11200,25 @@ 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[] = {
@@ -11050,6 +11233,11 @@ 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
 	{
@@ -11267,6 +11455,12 @@ 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/deadline.c b/kernel/sched/deadline.c
index 71b24371a..5a9a4b81c 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2246,6 +2246,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
 				     task_on_cpu(rq, task) ||
 				     !dl_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
@@ -2704,6 +2705,13 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 #endif
 }
 
+#ifdef CONFIG_SCHED_CORE
+static int task_is_throttled_dl(struct task_struct *p, int cpu)
+{
+	return p->dl.dl_throttled;
+}
+#endif
+
 DEFINE_SCHED_CLASS(dl) = {
 
 	.enqueue_task		= enqueue_task_dl,
@@ -2736,6 +2744,9 @@ DEFINE_SCHED_CLASS(dl) = {
 	.switched_to		= switched_to_dl,
 
 	.update_curr		= update_curr_dl,
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_dl,
+#endif
 };
 
 /* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 1637b65ba..d18686431 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -308,9 +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("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
 	debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity);
 
 	debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
@@ -535,9 +533,13 @@ 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);
 
@@ -547,6 +549,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
+#ifdef CONFIG_SCHED_BORE
+	SEQ_printf(m, " %2d", p->se.penalty_score);
+#endif
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
 #endif
@@ -580,10 +585,9 @@ 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 +601,25 @@ 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);
@@ -731,7 +734,7 @@ static void print_cpu(struct seq_file *m, int cpu)
 #define P(x)								\
 do {									\
 	if (sizeof(rq->x) == 4)						\
-		SEQ_printf(m, "  .%-30s: %ld\n", #x, (long)(rq->x));	\
+		SEQ_printf(m, "  .%-30s: %d\n", #x, (int)(rq->x));	\
 	else								\
 		SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x));\
 } while (0)
@@ -817,10 +820,7 @@ 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
@@ -1043,6 +1043,7 @@ 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 5f6587d94..faa608da0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -19,6 +19,9 @@
  *
  *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
  *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ *  Burst-Oriented Response Enhancer (BORE) CPU Scheduler
+ *  Copyright (C) 2021-2023 Masahito Suzuki <firelzrd@gmail.com>
  */
 #include <linux/energy_model.h>
 #include <linux/mmap_lock.h>
@@ -47,6 +50,7 @@
 #include <linux/psi.h>
 #include <linux/ratelimit.h>
 #include <linux/task_work.h>
+#include <linux/rbtree_augmented.h>
 
 #include <asm/switch_to.h>
 
@@ -56,22 +60,6 @@
 #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)
- */
-unsigned int sysctl_sched_latency			= 6000000ULL;
-static unsigned int normalized_sysctl_sched_latency	= 6000000ULL;
-
 /*
  * The initial- and re-scaling of tunables is configurable
  *
@@ -81,30 +69,17 @@ static unsigned int normalized_sysctl_sched_latency	= 6000000ULL;
  *   SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
  *   SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
  *
- * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
+ * (default SCHED_TUNABLESCALING_NONE = *1)
  */
-unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG;
+unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
  *
- * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 3 msec * 1, units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity			= 750000ULL;
-static unsigned int normalized_sysctl_sched_min_granularity	= 750000ULL;
-
-/*
- * 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			= 3000000ULL;
+static unsigned int normalized_sysctl_sched_base_slice	= 3000000ULL;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -119,13 +94,56 @@ unsigned int sysctl_sched_child_runs_first __read_mostly;
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  *
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 9.6 msec * 1, units: nanoseconds)
  */
-unsigned int sysctl_sched_wakeup_granularity			= 1000000UL;
-static unsigned int normalized_sysctl_sched_wakeup_granularity	= 1000000UL;
+unsigned int sysctl_sched_wakeup_granularity			= 9600000UL;
+static unsigned int normalized_sysctl_sched_wakeup_granularity	= 9600000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost	= 500000UL;
 
+#ifdef CONFIG_SCHED_BORE
+unsigned int __read_mostly sched_bore                 = 1;
+unsigned int __read_mostly sched_burst_cache_lifetime = 50000000;
+unsigned int __read_mostly sched_burst_penalty_offset = 12;
+unsigned int __read_mostly sched_burst_penalty_scale  = 1292;
+unsigned int __read_mostly sched_burst_smoothness     = 1;
+static int three          = 3;
+static int sixty_four     = 64;
+static int maxval_12_bits = 4095;
+
+static inline u32 __calc_bits10(u64 burst_time) {
+	u32 bits = fls64(burst_time);
+	u32 fdigs = likely(bits) ? bits - 1 : 0;
+	return (bits << 10) | (burst_time << (64 - fdigs) >> 54);
+}
+
+static inline u32 __calc_burst_score(u32 bits10, u32 offset) {
+	u32 val10 = max(0, (s32)bits10 - (s32)(offset << 10));
+	return min(39U, val10 * sched_burst_penalty_scale >> 20);
+}
+
+static void update_burst_score(struct sched_entity *se) {
+	u32 bits10 = __calc_bits10(se->max_burst_time);
+	se->penalty_score = __calc_burst_score(bits10, sched_burst_penalty_offset);
+}
+
+static inline u64 penalty_scale(u64 delta, struct sched_entity *se) {
+	return mul_u64_u32_shr(delta, sched_prio_to_wmult[se->penalty_score], 22);
+}
+
+static inline u64 binary_smooth(u64 old, u64 new, unsigned int smoothness) {
+	return (new + old * ((1 << smoothness) - 1)) >> smoothness;
+}
+
+static void reset_burst(struct sched_entity *se) {
+	se->prev_burst_time = binary_smooth(
+		se->prev_burst_time, se->burst_time, sched_burst_smoothness);
+	se->burst_time = 0;
+
+	se->max_burst_time = se->prev_burst_time;
+}
+#endif // CONFIG_SCHED_BORE
+
 int sched_thermal_decay_shift;
 static int __init setup_sched_thermal_decay_shift(char *str)
 {
@@ -185,6 +203,51 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
 
 #ifdef CONFIG_SYSCTL
 static struct ctl_table sched_fair_sysctls[] = {
+#ifdef CONFIG_SCHED_BORE
+	{
+		.procname	= "sched_bore",
+		.data		= &sched_bore,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "sched_burst_cache_lifetime",
+		.data		= &sched_burst_cache_lifetime,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler = proc_dointvec,
+	},
+	{
+		.procname	= "sched_burst_penalty_offset",
+		.data		= &sched_burst_penalty_offset,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &sixty_four,
+	},
+	{
+		.procname	= "sched_burst_penalty_scale",
+		.data		= &sched_burst_penalty_scale,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &maxval_12_bits,
+	},
+	{
+		.procname	= "sched_burst_smoothness",
+		.data		= &sched_burst_smoothness,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &three,
+	},
+#endif // CONFIG_SCHED_BORE
 	{
 		.procname       = "sched_child_runs_first",
 		.data           = &sysctl_sched_child_runs_first,
@@ -277,8 +340,7 @@ 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_base_slice);
 	SET_SYSCTL(sched_wakeup_granularity);
 #undef SET_SYSCTL
 }
@@ -347,6 +409,21 @@ 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);
+
+#ifdef CONFIG_SCHED_BORE
+	if (sched_bore)
+		return penalty_scale(delta, se);
+	else
+#endif // CONFIG_SCHED_BORE
+	return delta;
+}
 
 const struct sched_class fair_sched_class;
 
@@ -601,35 +678,229 @@ 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;
+	}
+
+	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;
 
-	/* ensure we never gain time by being placed backwards. */
-	u64_u32_store(cfs_rq->min_vruntime,
-		      max_vruntime(cfs_rq->min_vruntime, 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)
@@ -637,17 +908,51 @@ 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)
@@ -660,14 +965,81 @@ 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;
+		}
+
+		/*
+		 * 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;
+		}
 
-	return __node_2_se(next);
+		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
@@ -689,13 +1061,9 @@ 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_base_slice);
 	WRT_SYSCTL(sched_wakeup_granularity);
 #undef WRT_SYSCTL
 
@@ -703,90 +1071,44 @@ int sched_update_scaling(void)
 }
 #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);
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
 
 /*
- * 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 ((s64)(se->vruntime - se->deadline) < 0)
+		return;
 
-	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;
+	/*
+	 * EEVDF: vd_i = ve_i + r_i / w_i
+	 */
+	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
 
-		slice = max_t(u64, slice, min_gran);
+	/*
+	 * The task has consumed its request, reschedule.
+	 */
+	if (cfs_rq->nr_running > 1) {
+		resched_curr(rq_of(cfs_rq));
+		clear_buddies(cfs_rq, 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)
-{
-	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
 #include "pelt.h"
@@ -920,7 +1242,13 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
 
+#ifdef CONFIG_SCHED_BORE
+	curr->burst_time += delta_exec;
+	curr->max_burst_time = max(curr->max_burst_time, curr->burst_time);
+	update_burst_score(curr);
+#endif // CONFIG_SCHED_BORE
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
+	update_deadline(cfs_rq, curr);
 	update_min_vruntime(cfs_rq);
 
 	if (entity_is_task(curr)) {
@@ -1064,6 +1392,23 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+static inline bool is_core_idle(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+	int sibling;
+
+	for_each_cpu(sibling, cpu_smt_mask(cpu)) {
+		if (cpu == sibling)
+			continue;
+
+		if (!idle_cpu(sibling))
+			return false;
+	}
+#endif
+
+	return true;
+}
+
 #ifdef CONFIG_NUMA
 #define NUMA_IMBALANCE_MIN 2
 
@@ -1700,23 +2045,6 @@ struct numa_stats {
 	int idle_cpu;
 };
 
-static inline bool is_core_idle(int cpu)
-{
-#ifdef CONFIG_SCHED_SMT
-	int sibling;
-
-	for_each_cpu(sibling, cpu_smt_mask(cpu)) {
-		if (cpu == sibling)
-			continue;
-
-		if (!idle_cpu(sibling))
-			return false;
-	}
-#endif
-
-	return true;
-}
-
 struct task_numa_env {
 	struct task_struct *p;
 
@@ -3318,16 +3646,36 @@ 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);
+	} else {
+		s64 deadline = se->deadline - se->vruntime;
+		/*
+		 * When the weight changes, the virtual time slope changes and
+		 * we should adjust the relative virtual deadline accordingly.
+		 */
+		deadline = div_s64(deadline * old_weight, weight);
+		se->deadline = se->vruntime + deadline;
+	}
+
 #ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
@@ -3337,9 +3685,11 @@ 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)
@@ -4635,158 +4985,168 @@ 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.
@@ -4798,18 +5158,28 @@ 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;
@@ -4821,17 +5191,6 @@ 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) {
@@ -4843,27 +5202,10 @@ 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);
@@ -4897,20 +5239,12 @@ 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);
 
@@ -4929,52 +5263,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
 }
 
-/*
- * Preempt the current task with a newly woken task if needed:
- */
-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) {
-		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
 set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -5026,50 +5314,16 @@ 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 *candidate = pick_eevdf(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.
+	 * Enabling NEXT_BUDDY will affect latency but not fairness.
 	 */
-	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.
-	 */
-	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 (sched_feat(NEXT_BUDDY) &&
+	    cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next) && 
+			wakeup_preempt_entity(cfs_rq->next, candidate) < 1)
+		return cfs_rq->next;
 
-		if (second && wakeup_preempt_entity(second, left) < 1)
-			se = second;
-	}
-
-	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 candidate;
 }
 
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -5086,8 +5340,6 @@ 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. */
@@ -5128,9 +5380,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 			hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
 		return;
 #endif
-
-	if (cfs_rq->nr_running > 1)
-		check_preempt_tick(cfs_rq, curr);
 }
 
 
@@ -5959,6 +6208,10 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
 	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	cfs_b->period_timer.function = sched_cfs_period_timer;
+
+	/* Add a random offset so that timers interleave */
+	hrtimer_set_expires(&cfs_b->period_timer,
+			    get_random_u32_below(cfs_b->period));
 	hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	cfs_b->slack_timer.function = sched_cfs_slack_timer;
 	cfs_b->slack_started = false;
@@ -6131,13 +6384,12 @@ 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) {
@@ -6161,8 +6413,7 @@ 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
@@ -6203,17 +6454,6 @@ 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)
 {
@@ -6299,18 +6539,67 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	 * for the first enqueue operation of new tasks during the
 	 * overutilized flag detection.
 	 *
-	 * A better way of solving this problem would be to wait for
-	 * the PELT signals of tasks to converge before taking them
-	 * into account, but that is not straightforward to implement,
-	 * and the following generally works well enough in practice.
+	 * A better way of solving this problem would be to wait for
+	 * the PELT signals of tasks to converge before taking them
+	 * into account, but that is not straightforward to implement,
+	 * and the following generally works well enough in practice.
+	 */
+	if (!task_new)
+		update_overutilized_status(rq);
+
+enqueue_throttle:
+	assert_list_leaf_cfs_rq(rq);
+
+	hrtick_update(rq);
+}
+
+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.
 	 */
-	if (!task_new)
-		update_overutilized_status(rq);
+	return calc_delta_fair(gran, se);
+}
 
-enqueue_throttle:
-	assert_list_leaf_cfs_rq(rq);
+/*
+ * 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;
 
-	hrtick_update(rq);
+	if (vdiff <= 0)
+		return -1;
+
+	gran = wakeup_gran(se);
+	if (vdiff > gran)
+		return 1;
+
+	return 0;
 }
 
 static void set_next_buddy(struct sched_entity *se);
@@ -6331,6 +6620,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	util_est_dequeue(&rq->cfs, p);
 
 	for_each_sched_entity(se) {
+#ifdef CONFIG_SCHED_BORE
+		if (task_sleep) reset_burst(se);
+#endif // CONFIG_SCHED_BORE
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
 
@@ -6614,7 +6906,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->stats.nr_wakeups_affine_attempts);
-	if (target == nr_cpumask_bits)
+	if (target != this_cpu)
 		return prev_cpu;
 
 	schedstat_inc(sd->ttwu_move_affine);
@@ -7662,18 +7954,6 @@ 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);
 
@@ -7711,66 +7991,6 @@ 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) {
@@ -7782,12 +8002,6 @@ 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:
  */
@@ -7796,7 +8010,6 @@ 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;
 
@@ -7812,7 +8025,7 @@ 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;
 	}
@@ -7857,35 +8070,19 @@ 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) && (wakeup_preempt_entity(se, pse) == 1))
 		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
@@ -8086,14 +8283,15 @@ 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)
 {
 	struct task_struct *curr = rq->curr;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se;
+#ifdef CONFIG_SCHED_BORE
+	reset_burst(se);
+#endif // CONFIG_SCHED_BORE
 
 	/*
 	 * Are we the only task in the tree?
@@ -8103,21 +8301,19 @@ 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)
@@ -8360,8 +8556,7 @@ 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)
@@ -9270,96 +9465,61 @@ group_type group_classify(unsigned int imbalance_pct,
 }
 
 /**
- * asym_smt_can_pull_tasks - Check whether the load balancing CPU can pull tasks
- * @dst_cpu:	Destination CPU of the load balancing
+ * sched_use_asym_prio - Check whether asym_packing priority must be used
+ * @sd:		The scheduling domain of the load balancing
+ * @cpu:	A CPU
+ *
+ * Always use CPU priority when balancing load between SMT siblings. When
+ * balancing load between cores, it is not sufficient that @cpu is idle. Only
+ * use CPU priority if the whole core is idle.
+ *
+ * Returns: True if the priority of @cpu must be followed. False otherwise.
+ */
+static bool sched_use_asym_prio(struct sched_domain *sd, int cpu)
+{
+	if (!sched_smt_active())
+		return true;
+
+	return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu);
+}
+
+/**
+ * sched_asym - Check if the destination CPU can do asym_packing load balance
+ * @env:	The load balancing environment
  * @sds:	Load-balancing data with statistics of the local group
  * @sgs:	Load-balancing statistics of the candidate busiest group
- * @sg:		The candidate busiest group
+ * @group:	The candidate busiest group
  *
- * Check the state of the SMT siblings of both @sds::local and @sg and decide
- * if @dst_cpu can pull tasks.
+ * @env::dst_cpu can do asym_packing if it has higher priority than the
+ * preferred CPU of @group.
  *
- * If @dst_cpu does not have SMT siblings, it can pull tasks if two or more of
- * the SMT siblings of @sg are busy. If only one CPU in @sg is busy, pull tasks
- * only if @dst_cpu has higher priority.
+ * SMT is a special case. If we are balancing load between cores, @env::dst_cpu
+ * can do asym_packing balance only if all its SMT siblings are idle. Also, it
+ * can only do it if @group is an SMT group and has exactly on busy CPU. Larger
+ * imbalances in the number of CPUS are dealt with in find_busiest_group().
  *
- * If both @dst_cpu and @sg have SMT siblings, and @sg has exactly one more
- * busy CPU than @sds::local, let @dst_cpu pull tasks if it has higher priority.
- * Bigger imbalances in the number of busy CPUs will be dealt with in
- * update_sd_pick_busiest().
+ * If we are balancing load within an SMT core, or at DIE domain level, always
+ * proceed.
  *
- * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings
- * of @dst_cpu are idle and @sg has lower priority.
- *
- * Return: true if @dst_cpu can pull tasks, false otherwise.
+ * Return: true if @env::dst_cpu can do with asym_packing load balance. False
+ * otherwise.
  */
-static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds,
-				    struct sg_lb_stats *sgs,
-				    struct sched_group *sg)
+static inline bool
+sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
+	   struct sched_group *group)
 {
-#ifdef CONFIG_SCHED_SMT
-	bool local_is_smt, sg_is_smt;
-	int sg_busy_cpus;
-
-	local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY;
-	sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY;
-
-	sg_busy_cpus = sgs->group_weight - sgs->idle_cpus;
-
-	if (!local_is_smt) {
-		/*
-		 * If we are here, @dst_cpu is idle and does not have SMT
-		 * siblings. Pull tasks if candidate group has two or more
-		 * busy CPUs.
-		 */
-		if (sg_busy_cpus >= 2) /* implies sg_is_smt */
-			return true;
-
-		/*
-		 * @dst_cpu does not have SMT siblings. @sg may have SMT
-		 * siblings and only one is busy. In such case, @dst_cpu
-		 * can help if it has higher priority and is idle (i.e.,
-		 * it has no running tasks).
-		 */
-		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
-	}
-
-	/* @dst_cpu has SMT siblings. */
-
-	if (sg_is_smt) {
-		int local_busy_cpus = sds->local->group_weight -
-				      sds->local_stat.idle_cpus;
-		int busy_cpus_delta = sg_busy_cpus - local_busy_cpus;
-
-		if (busy_cpus_delta == 1)
-			return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
-
+	/* Ensure that the whole local core is idle, if applicable. */
+	if (!sched_use_asym_prio(env->sd, env->dst_cpu))
 		return false;
-	}
 
 	/*
-	 * @sg does not have SMT siblings. Ensure that @sds::local does not end
-	 * up with more than one busy SMT sibling and only pull tasks if there
-	 * are not busy CPUs (i.e., no CPU has running tasks).
+	 * CPU priorities does not make sense for SMT cores with more than one
+	 * busy sibling.
 	 */
-	if (!sds->local_stat.sum_nr_running)
-		return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu);
-
-	return false;
-#else
-	/* Always return false so that callers deal with non-SMT cases. */
-	return false;
-#endif
-}
-
-static inline bool
-sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs,
-	   struct sched_group *group)
-{
-	/* Only do SMT checks if either local or candidate have SMT siblings */
-	if ((sds->local->flags & SD_SHARE_CPUCAPACITY) ||
-	    (group->flags & SD_SHARE_CPUCAPACITY))
-		return asym_smt_can_pull_tasks(env->dst_cpu, sds, sgs, group);
+	if (group->flags & SD_SHARE_CPUCAPACITY) {
+		if (sgs->group_weight - sgs->idle_cpus != 1)
+			return false;
+	}
 
 	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
 }
@@ -9549,10 +9709,22 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 		 * contention when accessing shared HW resources.
 		 *
 		 * XXX for now avg_load is not computed and always 0 so we
-		 * select the 1st one.
+		 * select the 1st one, except if @sg is composed of SMT
+		 * siblings.
 		 */
-		if (sgs->avg_load <= busiest->avg_load)
+
+		if (sgs->avg_load < busiest->avg_load)
 			return false;
+
+		if (sgs->avg_load == busiest->avg_load) {
+			/*
+			 * SMT sched groups need more help than non-SMT groups.
+			 * If @sg happens to also be SMT, either choice is good.
+			 */
+			if (sds->busiest->flags & SD_SHARE_CPUCAPACITY)
+				return false;
+		}
+
 		break;
 
 	case group_has_spare:
@@ -10027,7 +10199,6 @@ static void update_idle_cpu_scan(struct lb_env *env,
 
 static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats *local = &sds->local_stat;
 	struct sg_lb_stats tmp_sgs;
@@ -10068,8 +10239,13 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		sg = sg->next;
 	} while (sg != env->sd->groups);
 
-	/* Tag domain that child domain prefers tasks go to siblings first */
-	sds->prefer_sibling = child && child->flags & SD_PREFER_SIBLING;
+	/*
+	 * Indicate that the child domain of the busiest group prefers tasks
+	 * go to a child's sibling domains first. NB the flags of a sched group
+	 * are those of the child domain.
+	 */
+	if (sds->busiest)
+		sds->prefer_sibling = !!(sds->busiest->flags & SD_PREFER_SIBLING);
 
 
 	if (env->sd->flags & SD_NUMA)
@@ -10379,7 +10555,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 			goto out_balanced;
 	}
 
-	/* Try to move all excess tasks to child's sibling domain */
+	/*
+	 * Try to move all excess tasks to a sibling domain of the busiest
+	 * group's child domain.
+	 */
 	if (sds.prefer_sibling && local->group_type == group_has_spare &&
 	    busiest->sum_nr_running > local->sum_nr_running + 1)
 		goto force_balance;
@@ -10481,8 +10660,15 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		    nr_running == 1)
 			continue;
 
-		/* Make sure we only pull tasks from a CPU of lower priority */
+		/*
+		 * Make sure we only pull tasks from a CPU of lower priority
+		 * when balancing between SMT siblings.
+		 *
+		 * If balancing between cores, let lower priority CPUs help
+		 * SMT cores with more than one busy sibling.
+		 */
 		if ((env->sd->flags & SD_ASYM_PACKING) &&
+		    sched_use_asym_prio(env->sd, i) &&
 		    sched_asym_prefer(i, env->dst_cpu) &&
 		    nr_running == 1)
 			continue;
@@ -10571,12 +10757,19 @@ static inline bool
 asym_active_balance(struct lb_env *env)
 {
 	/*
-	 * ASYM_PACKING needs to force migrate tasks from busy but
-	 * lower priority CPUs in order to pack all tasks in the
-	 * highest priority CPUs.
+	 * ASYM_PACKING needs to force migrate tasks from busy but lower
+	 * priority CPUs in order to pack all tasks in the highest priority
+	 * CPUs. When done between cores, do it only if the whole core if the
+	 * whole core is idle.
+	 *
+	 * If @env::src_cpu is an SMT core with busy siblings, let
+	 * the lower priority @env::dst_cpu help it. Do not follow
+	 * CPU priority.
 	 */
 	return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) &&
-	       sched_asym_prefer(env->dst_cpu, env->src_cpu);
+	       sched_use_asym_prio(env->sd, env->dst_cpu) &&
+	       (sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
+		!sched_use_asym_prio(env->sd, env->src_cpu));
 }
 
 static inline bool
@@ -11310,9 +11503,13 @@ static void nohz_balancer_kick(struct rq *rq)
 		 * When ASYM_PACKING; see if there's a more preferred CPU
 		 * currently idle; in which case, kick the ILB to move tasks
 		 * around.
+		 *
+		 * When balancing betwen cores, all the SMT siblings of the
+		 * preferred CPU must be idle.
 		 */
 		for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
-			if (sched_asym_prefer(i, cpu)) {
+			if (sched_use_asym_prio(sd, i) &&
+			    sched_asym_prefer(i, cpu)) {
 				flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
 				goto unlock;
 			}
@@ -11869,8 +12066,8 @@ 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);
 }
@@ -11976,6 +12173,18 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
 
 	return delta > 0;
 }
+
+static int task_is_throttled_fair(struct task_struct *p, int cpu)
+{
+	struct cfs_rq *cfs_rq;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	cfs_rq = task_group(p)->cfs_rq[cpu];
+#else
+	cfs_rq = &cpu_rq(cpu)->cfs;
+#endif
+	return throttled_hierarchy(cfs_rq);
+}
 #else
 static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
 #endif
@@ -12014,8 +12223,8 @@ 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;
 
@@ -12024,22 +12233,9 @@ 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);
 }
 
@@ -12068,34 +12264,6 @@ 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
@@ -12166,16 +12334,6 @@ 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);
 }
@@ -12183,12 +12341,8 @@ 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)
@@ -12299,6 +12453,7 @@ 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));
 
@@ -12397,6 +12552,9 @@ 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;
@@ -12527,6 +12685,29 @@ 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) { }
@@ -12553,7 +12734,7 @@ 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;
 }
@@ -12602,6 +12783,10 @@ DEFINE_SCHED_CLASS(fair) = {
 	.task_change_group	= task_change_group_fair,
 #endif
 
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_fair,
+#endif
+
 #ifdef CONFIG_UCLAMP_TASK
 	.uclamp_enabled		= 1,
 #endif
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76..26aa6c6d1 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -1,30 +1,26 @@
 /* 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
  * wakeup-preemption), since its likely going to consume data we
  * touched, increases cache locality.
  */
+#ifdef CONFIG_SCHED_BORE
+SCHED_FEAT(NEXT_BUDDY, true)
+#else // CONFIG_SCHED_BORE
 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)
+#endif // CONFIG_SCHED_BORE
 
 /*
  * Consider buddies to be cache hot, decreases the likeliness of a
@@ -98,6 +94,3 @@ 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/psi.c b/kernel/sched/psi.c
index 02e011cab..b49af594a 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -160,7 +160,6 @@ __setup("psi=", setup_psi);
 #define EXP_300s	2034		/* 1/exp(2s/300s) */
 
 /* PSI trigger definitions */
-#define WINDOW_MIN_US 500000	/* Min window size is 500ms */
 #define WINDOW_MAX_US 10000000	/* Max window size is 10s */
 #define UPDATES_PER_WINDOW 10	/* 10 updates per window */
 
@@ -186,17 +185,22 @@ static void group_init(struct psi_group *group)
 		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
 	group->avg_last_update = sched_clock();
 	group->avg_next_update = group->avg_last_update + psi_period;
-	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
 	mutex_init(&group->avgs_lock);
-	/* Init trigger-related members */
-	atomic_set(&group->poll_scheduled, 0);
-	mutex_init(&group->trigger_lock);
-	INIT_LIST_HEAD(&group->triggers);
-	group->poll_min_period = U32_MAX;
-	group->polling_next_update = ULLONG_MAX;
-	init_waitqueue_head(&group->poll_wait);
-	timer_setup(&group->poll_timer, poll_timer_fn, 0);
-	rcu_assign_pointer(group->poll_task, NULL);
+
+	/* Init avg trigger-related members */
+	INIT_LIST_HEAD(&group->avg_triggers);
+	memset(group->avg_nr_triggers, 0, sizeof(group->avg_nr_triggers));
+	INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
+
+	/* Init rtpoll trigger-related members */
+	atomic_set(&group->rtpoll_scheduled, 0);
+	mutex_init(&group->rtpoll_trigger_lock);
+	INIT_LIST_HEAD(&group->rtpoll_triggers);
+	group->rtpoll_min_period = U32_MAX;
+	group->rtpoll_next_update = ULLONG_MAX;
+	init_waitqueue_head(&group->rtpoll_wait);
+	timer_setup(&group->rtpoll_timer, poll_timer_fn, 0);
+	rcu_assign_pointer(group->rtpoll_task, NULL);
 }
 
 void __init psi_init(void)
@@ -384,92 +388,6 @@ static void collect_percpu_times(struct psi_group *group,
 		*pchanged_states = changed_states;
 }
 
-static u64 update_averages(struct psi_group *group, u64 now)
-{
-	unsigned long missed_periods = 0;
-	u64 expires, period;
-	u64 avg_next_update;
-	int s;
-
-	/* avgX= */
-	expires = group->avg_next_update;
-	if (now - expires >= psi_period)
-		missed_periods = div_u64(now - expires, psi_period);
-
-	/*
-	 * The periodic clock tick can get delayed for various
-	 * reasons, especially on loaded systems. To avoid clock
-	 * drift, we schedule the clock in fixed psi_period intervals.
-	 * But the deltas we sample out of the per-cpu buckets above
-	 * are based on the actual time elapsing between clock ticks.
-	 */
-	avg_next_update = expires + ((1 + missed_periods) * psi_period);
-	period = now - (group->avg_last_update + (missed_periods * psi_period));
-	group->avg_last_update = now;
-
-	for (s = 0; s < NR_PSI_STATES - 1; s++) {
-		u32 sample;
-
-		sample = group->total[PSI_AVGS][s] - group->avg_total[s];
-		/*
-		 * Due to the lockless sampling of the time buckets,
-		 * recorded time deltas can slip into the next period,
-		 * which under full pressure can result in samples in
-		 * excess of the period length.
-		 *
-		 * We don't want to report non-sensical pressures in
-		 * excess of 100%, nor do we want to drop such events
-		 * on the floor. Instead we punt any overage into the
-		 * future until pressure subsides. By doing this we
-		 * don't underreport the occurring pressure curve, we
-		 * just report it delayed by one period length.
-		 *
-		 * The error isn't cumulative. As soon as another
-		 * delta slips from a period P to P+1, by definition
-		 * it frees up its time T in P.
-		 */
-		if (sample > period)
-			sample = period;
-		group->avg_total[s] += sample;
-		calc_avgs(group->avg[s], missed_periods, sample, period);
-	}
-
-	return avg_next_update;
-}
-
-static void psi_avgs_work(struct work_struct *work)
-{
-	struct delayed_work *dwork;
-	struct psi_group *group;
-	u32 changed_states;
-	u64 now;
-
-	dwork = to_delayed_work(work);
-	group = container_of(dwork, struct psi_group, avgs_work);
-
-	mutex_lock(&group->avgs_lock);
-
-	now = sched_clock();
-
-	collect_percpu_times(group, PSI_AVGS, &changed_states);
-	/*
-	 * If there is task activity, periodically fold the per-cpu
-	 * times and feed samples into the running averages. If things
-	 * are idle and there is no data to process, stop the clock.
-	 * Once restarted, we'll catch up the running averages in one
-	 * go - see calc_avgs() and missed_periods.
-	 */
-	if (now >= group->avg_next_update)
-		group->avg_next_update = update_averages(group, now);
-
-	if (changed_states & PSI_STATE_RESCHEDULE) {
-		schedule_delayed_work(dwork, nsecs_to_jiffies(
-				group->avg_next_update - now) + 1);
-	}
-
-	mutex_unlock(&group->avgs_lock);
-}
-
 /* Trigger tracking window manipulations */
 static void window_reset(struct psi_window *win, u64 now, u64 value,
 			 u64 prev_growth)
@@ -516,33 +434,32 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
 	return growth;
 }
 
-static void init_triggers(struct psi_group *group, u64 now)
-{
-	struct psi_trigger *t;
-
-	list_for_each_entry(t, &group->triggers, node)
-		window_reset(&t->win, now,
-				group->total[PSI_POLL][t->state], 0);
-	memcpy(group->polling_total, group->total[PSI_POLL],
-		   sizeof(group->polling_total));
-	group->polling_next_update = now + group->poll_min_period;
-}
-
-static u64 update_triggers(struct psi_group *group, u64 now)
+static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
+						   enum psi_aggregators aggregator)
 {
 	struct psi_trigger *t;
-	bool update_total = false;
-	u64 *total = group->total[PSI_POLL];
+	u64 *total = group->total[aggregator];
+	struct list_head *triggers;
+	u64 *aggregator_total;
+	*update_total = false;
+
+	if (aggregator == PSI_AVGS) {
+		triggers = &group->avg_triggers;
+		aggregator_total = group->avg_total;
+	} else {
+		triggers = &group->rtpoll_triggers;
+		aggregator_total = group->rtpoll_total;
+	}
 
 	/*
 	 * On subsequent updates, calculate growth deltas and let
 	 * watchers know when their specified thresholds are exceeded.
 	 */
-	list_for_each_entry(t, &group->triggers, node) {
+	list_for_each_entry(t, triggers, node) {
 		u64 growth;
 		bool new_stall;
 
-		new_stall = group->polling_total[t->state] != total[t->state];
+		new_stall = aggregator_total[t->state] != total[t->state];
 
 		/* Check for stall activity or a previous threshold breach */
 		if (!new_stall && !t->pending_event)
@@ -560,7 +477,7 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 			 * been through all of them. Also remember to extend the
 			 * polling time if we see new stall activity.
 			 */
-			update_total = true;
+			*update_total = true;
 
 			/* Calculate growth since last update */
 			growth = window_update(&t->win, now, total[t->state]);
@@ -583,52 +500,150 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 		t->pending_event = false;
 	}
 
-	if (update_total)
-		memcpy(group->polling_total, total,
-				sizeof(group->polling_total));
+	return now + group->rtpoll_min_period;
+}
+
+static u64 update_averages(struct psi_group *group, u64 now)
+{
+	unsigned long missed_periods = 0;
+	u64 expires, period;
+	u64 avg_next_update;
+	int s;
+
+	/* avgX= */
+	expires = group->avg_next_update;
+	if (now - expires >= psi_period)
+		missed_periods = div_u64(now - expires, psi_period);
+
+	/*
+	 * The periodic clock tick can get delayed for various
+	 * reasons, especially on loaded systems. To avoid clock
+	 * drift, we schedule the clock in fixed psi_period intervals.
+	 * But the deltas we sample out of the per-cpu buckets above
+	 * are based on the actual time elapsing between clock ticks.
+	 */
+	avg_next_update = expires + ((1 + missed_periods) * psi_period);
+	period = now - (group->avg_last_update + (missed_periods * psi_period));
+	group->avg_last_update = now;
+
+	for (s = 0; s < NR_PSI_STATES - 1; s++) {
+		u32 sample;
+
+		sample = group->total[PSI_AVGS][s] - group->avg_total[s];
+		/*
+		 * Due to the lockless sampling of the time buckets,
+		 * recorded time deltas can slip into the next period,
+		 * which under full pressure can result in samples in
+		 * excess of the period length.
+		 *
+		 * We don't want to report non-sensical pressures in
+		 * excess of 100%, nor do we want to drop such events
+		 * on the floor. Instead we punt any overage into the
+		 * future until pressure subsides. By doing this we
+		 * don't underreport the occurring pressure curve, we
+		 * just report it delayed by one period length.
+		 *
+		 * The error isn't cumulative. As soon as another
+		 * delta slips from a period P to P+1, by definition
+		 * it frees up its time T in P.
+		 */
+		if (sample > period)
+			sample = period;
+		group->avg_total[s] += sample;
+		calc_avgs(group->avg[s], missed_periods, sample, period);
+	}
+
+	return avg_next_update;
+}
+
+static void psi_avgs_work(struct work_struct *work)
+{
+	struct delayed_work *dwork;
+	struct psi_group *group;
+	u32 changed_states;
+	bool update_total;
+	u64 now;
+
+	dwork = to_delayed_work(work);
+	group = container_of(dwork, struct psi_group, avgs_work);
+
+	mutex_lock(&group->avgs_lock);
+
+	now = sched_clock();
+
+	collect_percpu_times(group, PSI_AVGS, &changed_states);
+	/*
+	 * If there is task activity, periodically fold the per-cpu
+	 * times and feed samples into the running averages. If things
+	 * are idle and there is no data to process, stop the clock.
+	 * Once restarted, we'll catch up the running averages in one
+	 * go - see calc_avgs() and missed_periods.
+	 */
+	if (now >= group->avg_next_update) {
+		update_triggers(group, now, &update_total, PSI_AVGS);
+		group->avg_next_update = update_averages(group, now);
+	}
+
+	if (changed_states & PSI_STATE_RESCHEDULE) {
+		schedule_delayed_work(dwork, nsecs_to_jiffies(
+				group->avg_next_update - now) + 1);
+	}
 
-	return now + group->poll_min_period;
+	mutex_unlock(&group->avgs_lock);
+}
+
+static void init_rtpoll_triggers(struct psi_group *group, u64 now)
+{
+	struct psi_trigger *t;
+
+	list_for_each_entry(t, &group->rtpoll_triggers, node)
+		window_reset(&t->win, now,
+				group->total[PSI_POLL][t->state], 0);
+	memcpy(group->rtpoll_total, group->total[PSI_POLL],
+		   sizeof(group->rtpoll_total));
+	group->rtpoll_next_update = now + group->rtpoll_min_period;
 }
 
 /* Schedule polling if it's not already scheduled or forced. */
-static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay,
+static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay,
 				   bool force)
 {
 	struct task_struct *task;
 
 	/*
 	 * atomic_xchg should be called even when !force to provide a
-	 * full memory barrier (see the comment inside psi_poll_work).
+	 * full memory barrier (see the comment inside psi_rtpoll_work).
 	 */
-	if (atomic_xchg(&group->poll_scheduled, 1) && !force)
+	if (atomic_xchg(&group->rtpoll_scheduled, 1) && !force)
 		return;
 
 	rcu_read_lock();
 
-	task = rcu_dereference(group->poll_task);
+	task = rcu_dereference(group->rtpoll_task);
 	/*
 	 * kworker might be NULL in case psi_trigger_destroy races with
 	 * psi_task_change (hotpath) which can't use locks
 	 */
 	if (likely(task))
-		mod_timer(&group->poll_timer, jiffies + delay);
+		mod_timer(&group->rtpoll_timer, jiffies + delay);
 	else
-		atomic_set(&group->poll_scheduled, 0);
+		atomic_set(&group->rtpoll_scheduled, 0);
 
 	rcu_read_unlock();
 }
 
-static void psi_poll_work(struct psi_group *group)
+static void psi_rtpoll_work(struct psi_group *group)
 {
 	bool force_reschedule = false;
 	u32 changed_states;
+	bool update_total;
 	u64 now;
 
-	mutex_lock(&group->trigger_lock);
+	mutex_lock(&group->rtpoll_trigger_lock);
 
 	now = sched_clock();
 
-	if (now > group->polling_until) {
+	if (now > group->rtpoll_until) {
 		/*
 		 * We are either about to start or might stop polling if no
 		 * state change was recorded. Resetting poll_scheduled leaves
@@ -638,7 +653,7 @@ static void psi_poll_work(struct psi_group *group)
 		 * should be negligible and polling_next_update still keeps
 		 * updates correctly on schedule.
 		 */
-		atomic_set(&group->poll_scheduled, 0);
+		atomic_set(&group->rtpoll_scheduled, 0);
 		/*
 		 * A task change can race with the poll worker that is supposed to
 		 * report on it. To avoid missing events, ensure ordering between
@@ -667,60 +682,64 @@ static void psi_poll_work(struct psi_group *group)
 
 	collect_percpu_times(group, PSI_POLL, &changed_states);
 
-	if (changed_states & group->poll_states) {
+	if (changed_states & group->rtpoll_states) {
 		/* Initialize trigger windows when entering polling mode */
-		if (now > group->polling_until)
-			init_triggers(group, now);
+		if (now > group->rtpoll_until)
+			init_rtpoll_triggers(group, now);
 
 		/*
 		 * Keep the monitor active for at least the duration of the
 		 * minimum tracking window as long as monitor states are
 		 * changing.
 		 */
-		group->polling_until = now +
-			group->poll_min_period * UPDATES_PER_WINDOW;
+		group->rtpoll_until = now +
+			group->rtpoll_min_period * UPDATES_PER_WINDOW;
 	}
 
-	if (now > group->polling_until) {
-		group->polling_next_update = ULLONG_MAX;
+	if (now > group->rtpoll_until) {
+		group->rtpoll_next_update = ULLONG_MAX;
 		goto out;
 	}
 
-	if (now >= group->polling_next_update)
-		group->polling_next_update = update_triggers(group, now);
+	if (now >= group->rtpoll_next_update) {
+		group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL);
+		if (update_total)
+			memcpy(group->rtpoll_total, group->total[PSI_POLL],
+				   sizeof(group->rtpoll_total));
+	}
 
-	psi_schedule_poll_work(group,
-		nsecs_to_jiffies(group->polling_next_update - now) + 1,
+	psi_schedule_rtpoll_work(group,
+		nsecs_to_jiffies(group->rtpoll_next_update - now) + 1,
 		force_reschedule);
 
 out:
-	mutex_unlock(&group->trigger_lock);
+	mutex_unlock(&group->rtpoll_trigger_lock);
 }
 
-static int psi_poll_worker(void *data)
+static int psi_rtpoll_worker(void *data)
 {
 	struct psi_group *group = (struct psi_group *)data;
 
 	sched_set_fifo_low(current);
 
 	while (true) {
-		wait_event_interruptible(group->poll_wait,
-				atomic_cmpxchg(&group->poll_wakeup, 1, 0) ||
+		wait_event_interruptible(group->rtpoll_wait,
+				atomic_cmpxchg(&group->rtpoll_wakeup, 1, 0) ||
 				kthread_should_stop());
 		if (kthread_should_stop())
 			break;
 
-		psi_poll_work(group);
+		psi_rtpoll_work(group);
 	}
 	return 0;
 }
 
 static void poll_timer_fn(struct timer_list *t)
 {
-	struct psi_group *group = from_timer(group, t, poll_timer);
+	struct psi_group *group = from_timer(group, t, rtpoll_timer);
 
-	atomic_set(&group->poll_wakeup, 1);
-	wake_up_interruptible(&group->poll_wait);
+	atomic_set(&group->rtpoll_wakeup, 1);
+	wake_up_interruptible(&group->rtpoll_wait);
 }
 
 static void record_times(struct psi_group_cpu *groupc, u64 now)
@@ -851,8 +870,8 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 	write_seqcount_end(&groupc->seq);
 
-	if (state_mask & group->poll_states)
-		psi_schedule_poll_work(group, 1, false);
+	if (state_mask & group->rtpoll_states)
+		psi_schedule_rtpoll_work(group, 1, false);
 
 	if (wake_clock && !delayed_work_pending(&group->avgs_work))
 		schedule_delayed_work(&group->avgs_work, PSI_FREQ);
@@ -1005,8 +1024,8 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
 
 		write_seqcount_end(&groupc->seq);
 
-		if (group->poll_states & (1 << PSI_IRQ_FULL))
-			psi_schedule_poll_work(group, 1, false);
+		if (group->rtpoll_states & (1 << PSI_IRQ_FULL))
+			psi_schedule_rtpoll_work(group, 1, false);
 	} while ((group = group->parent));
 }
 #endif
@@ -1101,7 +1120,7 @@ void psi_cgroup_free(struct cgroup *cgroup)
 	cancel_delayed_work_sync(&cgroup->psi->avgs_work);
 	free_percpu(cgroup->psi->pcpu);
 	/* All triggers must be removed by now */
-	WARN_ONCE(cgroup->psi->poll_states, "psi: trigger leak\n");
+	WARN_ONCE(cgroup->psi->rtpoll_states, "psi: trigger leak\n");
 	kfree(cgroup->psi);
 }
 
@@ -1253,16 +1272,23 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 }
 
 struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res)
+			char *buf, enum psi_res res, struct file *file)
 {
 	struct psi_trigger *t;
 	enum psi_states state;
 	u32 threshold_us;
+	bool privileged;
 	u32 window_us;
 
 	if (static_branch_likely(&psi_disabled))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	/*
+	 * Checking the privilege here on file->f_cred implies that a privileged user
+	 * could open the file and delegate the write to an unprivileged one.
+	 */
+	privileged = cap_raised(file->f_cred->cap_effective, CAP_SYS_RESOURCE);
+
 	if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2)
 		state = PSI_IO_SOME + res * 2;
 	else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2)
@@ -1278,8 +1304,14 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	if (state >= PSI_NONIDLE)
 		return ERR_PTR(-EINVAL);
 
-	if (window_us < WINDOW_MIN_US ||
-		window_us > WINDOW_MAX_US)
+	if (window_us == 0 || window_us > WINDOW_MAX_US)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Unprivileged users can only use 2s windows so that averages aggregation
+	 * work is used, and no RT threads need to be spawned.
+	 */
+	if (!privileged && window_us % 2000000)
 		return ERR_PTR(-EINVAL);
 
 	/* Check threshold */
@@ -1301,31 +1333,40 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
 	t->pending_event = false;
+	t->aggregator = privileged ? PSI_POLL : PSI_AVGS;
 
-	mutex_lock(&group->trigger_lock);
+	if (privileged) {
+		mutex_lock(&group->rtpoll_trigger_lock);
 
-	if (!rcu_access_pointer(group->poll_task)) {
-		struct task_struct *task;
+		if (!rcu_access_pointer(group->rtpoll_task)) {
+			struct task_struct *task;
 
-		task = kthread_create(psi_poll_worker, group, "psimon");
-		if (IS_ERR(task)) {
-			kfree(t);
-			mutex_unlock(&group->trigger_lock);
-			return ERR_CAST(task);
+			task = kthread_create(psi_rtpoll_worker, group, "psimon");
+			if (IS_ERR(task)) {
+				kfree(t);
+				mutex_unlock(&group->rtpoll_trigger_lock);
+				return ERR_CAST(task);
+			}
+			atomic_set(&group->rtpoll_wakeup, 0);
+			wake_up_process(task);
+			rcu_assign_pointer(group->rtpoll_task, task);
 		}
-		atomic_set(&group->poll_wakeup, 0);
-		wake_up_process(task);
-		rcu_assign_pointer(group->poll_task, task);
-	}
 
-	list_add(&t->node, &group->triggers);
-	group->poll_min_period = min(group->poll_min_period,
-		div_u64(t->win.size, UPDATES_PER_WINDOW));
-	group->nr_triggers[t->state]++;
-	group->poll_states |= (1 << t->state);
+		list_add(&t->node, &group->rtpoll_triggers);
+		group->rtpoll_min_period = min(group->rtpoll_min_period,
+			div_u64(t->win.size, UPDATES_PER_WINDOW));
+		group->rtpoll_nr_triggers[t->state]++;
+		group->rtpoll_states |= (1 << t->state);
+
+		mutex_unlock(&group->rtpoll_trigger_lock);
+	} else {
+		mutex_lock(&group->avgs_lock);
 
-	mutex_unlock(&group->trigger_lock);
+		list_add(&t->node, &group->avg_triggers);
+		group->avg_nr_triggers[t->state]++;
 
+		mutex_unlock(&group->avgs_lock);
+	}
 	return t;
 }
 
@@ -1349,51 +1390,59 @@ void psi_trigger_destroy(struct psi_trigger *t)
 	 */
 	wake_up_pollfree(&t->event_wait);
 
-	mutex_lock(&group->trigger_lock);
-
-	if (!list_empty(&t->node)) {
-		struct psi_trigger *tmp;
-		u64 period = ULLONG_MAX;
-
-		list_del(&t->node);
-		group->nr_triggers[t->state]--;
-		if (!group->nr_triggers[t->state])
-			group->poll_states &= ~(1 << t->state);
-		/* reset min update period for the remaining triggers */
-		list_for_each_entry(tmp, &group->triggers, node)
-			period = min(period, div_u64(tmp->win.size,
-					UPDATES_PER_WINDOW));
-		group->poll_min_period = period;
-		/* Destroy poll_task when the last trigger is destroyed */
-		if (group->poll_states == 0) {
-			group->polling_until = 0;
-			task_to_destroy = rcu_dereference_protected(
-					group->poll_task,
-					lockdep_is_held(&group->trigger_lock));
-			rcu_assign_pointer(group->poll_task, NULL);
-			del_timer(&group->poll_timer);
+	if (t->aggregator == PSI_AVGS) {
+		mutex_lock(&group->avgs_lock);
+		if (!list_empty(&t->node)) {
+			list_del(&t->node);
+			group->avg_nr_triggers[t->state]--;
 		}
+		mutex_unlock(&group->avgs_lock);
+	} else {
+		mutex_lock(&group->rtpoll_trigger_lock);
+		if (!list_empty(&t->node)) {
+			struct psi_trigger *tmp;
+			u64 period = ULLONG_MAX;
+
+			list_del(&t->node);
+			group->rtpoll_nr_triggers[t->state]--;
+			if (!group->rtpoll_nr_triggers[t->state])
+				group->rtpoll_states &= ~(1 << t->state);
+			/* reset min update period for the remaining triggers */
+			list_for_each_entry(tmp, &group->rtpoll_triggers, node)
+				period = min(period, div_u64(tmp->win.size,
+						UPDATES_PER_WINDOW));
+			group->rtpoll_min_period = period;
+			/* Destroy rtpoll_task when the last trigger is destroyed */
+			if (group->rtpoll_states == 0) {
+				group->rtpoll_until = 0;
+				task_to_destroy = rcu_dereference_protected(
+						group->rtpoll_task,
+						lockdep_is_held(&group->rtpoll_trigger_lock));
+				rcu_assign_pointer(group->rtpoll_task, NULL);
+				del_timer(&group->rtpoll_timer);
+			}
+		}
+		mutex_unlock(&group->rtpoll_trigger_lock);
 	}
 
-	mutex_unlock(&group->trigger_lock);
-
 	/*
-	 * Wait for psi_schedule_poll_work RCU to complete its read-side
+	 * Wait for psi_schedule_rtpoll_work RCU to complete its read-side
 	 * critical section before destroying the trigger and optionally the
-	 * poll_task.
+	 * rtpoll_task.
 	 */
 	synchronize_rcu();
 	/*
-	 * Stop kthread 'psimon' after releasing trigger_lock to prevent a
-	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
+	 * Stop kthread 'psimon' after releasing rtpoll_trigger_lock to prevent
+	 * a deadlock while waiting for psi_rtpoll_work to acquire
+	 * rtpoll_trigger_lock
 	 */
 	if (task_to_destroy) {
 		/*
 		 * After the RCU grace period has expired, the worker
-		 * can no longer be found through group->poll_task.
+		 * can no longer be found through group->rtpoll_task.
 		 */
 		kthread_stop(task_to_destroy);
-		atomic_set(&group->poll_scheduled, 0);
+		atomic_set(&group->rtpoll_scheduled, 0);
 	}
 	kfree(t);
 }
@@ -1435,27 +1484,19 @@ static int psi_cpu_show(struct seq_file *m, void *v)
 	return psi_show(m, &psi_system, PSI_CPU);
 }
 
-static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *))
-{
-	if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE))
-		return -EPERM;
-
-	return single_open(file, psi_show, NULL);
-}
-
 static int psi_io_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_io_show);
+	return single_open(file, psi_io_show, NULL);
 }
 
 static int psi_memory_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_memory_show);
+	return single_open(file, psi_memory_show, NULL);
 }
 
 static int psi_cpu_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_cpu_show);
+	return single_open(file, psi_cpu_show, NULL);
 }
 
 static ssize_t psi_write(struct file *file, const char __user *user_buf,
@@ -1489,7 +1530,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 		return -EBUSY;
 	}
 
-	new = psi_trigger_create(&psi_system, buf, res);
+	new = psi_trigger_create(&psi_system, buf, res, file);
 	if (IS_ERR(new)) {
 		mutex_unlock(&seq->lock);
 		return PTR_ERR(new);
@@ -1569,7 +1610,7 @@ static int psi_irq_show(struct seq_file *m, void *v)
 
 static int psi_irq_open(struct inode *inode, struct file *file)
 {
-	return psi_open(file, psi_irq_show);
+	return single_open(file, psi_irq_show, NULL);
 }
 
 static ssize_t psi_irq_write(struct file *file, const char __user *user_buf,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0a11f44ad..00e0e5074 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2000,11 +2000,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * the mean time, task could have
 			 * migrated already or had its affinity changed.
 			 * Also make sure that it wasn't scheduled on its rq.
+			 * It is possible the task was scheduled, set
+			 * "migrate_disabled" and then got preempted, so we must
+			 * check the task migration disable flag here too.
 			 */
 			if (unlikely(task_rq(task) != rq ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
 				     task_on_cpu(rq, task) ||
 				     !rt_task(task) ||
+				     is_migration_disabled(task) ||
 				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);
@@ -2677,6 +2681,21 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 		return 0;
 }
 
+#ifdef CONFIG_SCHED_CORE
+static int task_is_throttled_rt(struct task_struct *p, int cpu)
+{
+	struct rt_rq *rt_rq;
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	rt_rq = task_group(p)->rt_rq[cpu];
+#else
+	rt_rq = &cpu_rq(cpu)->rt;
+#endif
+
+	return rt_rq_throttled(rt_rq);
+}
+#endif
+
 DEFINE_SCHED_CLASS(rt) = {
 
 	.enqueue_task		= enqueue_task_rt,
@@ -2710,6 +2729,10 @@ DEFINE_SCHED_CLASS(rt) = {
 
 	.update_curr		= update_curr_rt,
 
+#ifdef CONFIG_SCHED_CORE
+	.task_is_throttled	= task_is_throttled_rt,
+#endif
+
 #ifdef CONFIG_UCLAMP_TASK
 	.uclamp_enabled		= 1,
 #endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3e8df6d31..00977849b 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;
@@ -1772,6 +1778,13 @@ queue_balance_callback(struct rq *rq,
 	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
 			__sd; __sd = __sd->parent)
 
+/* A mask of all the SD flags that have the SDF_SHARED_CHILD metaflag */
+#define SD_FLAG(name, mflags) (name * !!((mflags) & SDF_SHARED_CHILD)) |
+static const unsigned int SD_SHARED_CHILD_MASK =
+#include <linux/sched/sd_flags.h>
+0;
+#undef SD_FLAG
+
 /**
  * highest_flag_domain - Return highest sched_domain containing flag.
  * @cpu:	The CPU whose highest level of sched domain is to
@@ -1779,16 +1792,25 @@ queue_balance_callback(struct rq *rq,
  * @flag:	The flag to check for the highest sched_domain
  *		for the given CPU.
  *
- * Returns the highest sched_domain of a CPU which contains the given flag.
+ * Returns the highest sched_domain of a CPU which contains @flag. If @flag has
+ * the SDF_SHARED_CHILD metaflag, all the children domains also have @flag.
  */
 static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
 {
 	struct sched_domain *sd, *hsd = NULL;
 
 	for_each_domain(cpu, sd) {
-		if (!(sd->flags & flag))
+		if (sd->flags & flag) {
+			hsd = sd;
+			continue;
+		}
+
+		/*
+		 * Stop the search if @flag is known to be shared at lower
+		 * levels. It will not be found further up.
+		 */
+		if (flag & SD_SHARED_CHILD_MASK)
 			break;
-		hsd = sd;
 	}
 
 	return hsd;
@@ -2137,7 +2159,7 @@ 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
@@ -2157,6 +2179,7 @@ extern const u32		sched_prio_to_wmult[40];
 #else
 #define ENQUEUE_MIGRATED	0x00
 #endif
+#define ENQUEUE_INITIAL		0x80
 
 #define RETRY_TASK		((void *)-1UL)
 
@@ -2224,6 +2247,10 @@ struct sched_class {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_change_group)(struct task_struct *p);
 #endif
+
+#ifdef CONFIG_SCHED_CORE
+	int (*task_is_throttled)(struct task_struct *p, int cpu);
+#endif
 };
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
@@ -2459,9 +2486,7 @@ 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_base_slice;
 extern unsigned int sysctl_sched_wakeup_granularity;
 extern int sysctl_resched_latency_warn_ms;
 extern int sysctl_resched_latency_warn_once;
@@ -2475,6 +2500,8 @@ 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
 
 /*
@@ -3306,4 +3333,7 @@ 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/kernel/sched/topology.c b/kernel/sched/topology.c
index 051aaf65c..ca4472281 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -209,8 +209,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 DEFINE_STATIC_KEY_FALSE(sched_energy_present);
 static unsigned int sysctl_sched_energy_aware = 1;
-DEFINE_MUTEX(sched_energy_mutex);
-bool sched_energy_update;
+static DEFINE_MUTEX(sched_energy_mutex);
+static bool sched_energy_update;
 
 void rebuild_sched_domains_energy(void)
 {
@@ -719,8 +719,13 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 
 		if (sd_parent_degenerate(tmp, parent)) {
 			tmp->parent = parent->parent;
-			if (parent->parent)
+
+			if (parent->parent) {
 				parent->parent->child = tmp;
+				if (tmp->flags & SD_SHARE_CPUCAPACITY)
+					parent->parent->groups->flags |= SD_SHARE_CPUCAPACITY;
+			}
+
 			/*
 			 * Transfer SD_PREFER_SIBLING down in case of a
 			 * degenerate parent; the spans match for this
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 3bac0a8ce..b2e932c25 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 */
-- 
2.40.1.445.gf85cd430b1

Places

File _service:download_files:0001-bore-6.3-introduce-BORE-Scheduler-with-EEVDF-patches.patch of Package linux-px (Revision 41496267b0e9ba6e75fd24ffbbfd5e00)

Places