From 3dc167ba5729ddd2d8e3fa1841653792c295d3f1 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 19 May 2020 19:25:06 +0200
Subject: sched/cputime: Improve cputime_adjust()

People report that utime and stime from /proc/<pid>/stat become very
wrong when the numbers are big enough, especially if you watch these
counters incrementally.

Specifically, the current implementation of: stime*rtime/total,
results in a saw-tooth function on top of the desired line, where the
teeth grow in size the larger the values become. IOW, it has a
relative error.

The result is that, when watching incrementally as time progresses
(for large values), we'll see periods of pure stime or utime increase,
irrespective of the actual ratio we're striving for.

Replace scale_stime() with a math64.h helper: mul_u64_u64_div_u64()
that is far more accurate. This also allows architectures to override
the implementation -- for instance they can opt for the old algorithm
if this new one turns out to be too expensive for them.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200519172506.GA317395@hirez.programming.kicks-ass.net
---
 include/linux/math64.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/math64.h b/include/linux/math64.h
index 11a267413e8e..d097119419e6 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -263,6 +263,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
+u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
+
 #define DIV64_U64_ROUND_UP(ll, d)	\
 	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
 
-- 
cgit v1.2.3


From 461daba06bdcb9c7a3f92b9bbd110e1f7d093ffc Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Thu, 28 May 2020 12:54:42 -0700
Subject: psi: eliminate kthread_worker from psi trigger scheduling mechanism

Each psi group requires a dedicated kthread_delayed_work and
kthread_worker. Since no other work can be performed using psi_group's
kthread_worker, the same result can be obtained using a task_struct and
a timer directly. This makes psi triggering simpler by removing lists
and locks involved with kthread_worker usage and eliminates the need for
poll_scheduled atomic use in the hot path.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200528195442.190116-1-surenb@google.com
---
 include/linux/psi_types.h |   7 +--
 kernel/sched/psi.c        | 113 ++++++++++++++++++++++++++--------------------
 2 files changed, 68 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 4b7258495a04..b95f3211566a 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -153,9 +153,10 @@ struct psi_group {
 	unsigned long avg[NR_PSI_STATES - 1][3];
 
 	/* Monitor work control */
-	atomic_t poll_scheduled;
-	struct kthread_worker __rcu *poll_kworker;
-	struct kthread_delayed_work poll_work;
+	struct task_struct __rcu *poll_task;
+	struct timer_list poll_timer;
+	wait_queue_head_t poll_wait;
+	atomic_t poll_wakeup;
 
 	/* Protects data used by the monitor */
 	struct mutex trigger_lock;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 8f45cdb6463b..e53b711bd643 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -190,7 +190,6 @@ static void group_init(struct psi_group *group)
 	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);
 	memset(group->nr_triggers, 0, sizeof(group->nr_triggers));
@@ -199,7 +198,7 @@ static void group_init(struct psi_group *group)
 	memset(group->polling_total, 0, sizeof(group->polling_total));
 	group->polling_next_update = ULLONG_MAX;
 	group->polling_until = 0;
-	rcu_assign_pointer(group->poll_kworker, NULL);
+	rcu_assign_pointer(group->poll_task, NULL);
 }
 
 void __init psi_init(void)
@@ -547,47 +546,38 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	return now + group->poll_min_period;
 }
 
-/*
- * Schedule polling if it's not already scheduled. It's safe to call even from
- * hotpath because even though kthread_queue_delayed_work takes worker->lock
- * spinlock that spinlock is never contended due to poll_scheduled atomic
- * preventing such competition.
- */
+/* Schedule polling if it's not already scheduled. */
 static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
 {
-	struct kthread_worker *kworker;
+	struct task_struct *task;
 
-	/* Do not reschedule if already scheduled */
-	if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0)
+	/*
+	 * Do not reschedule if already scheduled.
+	 * Possible race with a timer scheduled after this check but before
+	 * mod_timer below can be tolerated because group->polling_next_update
+	 * will keep updates on schedule.
+	 */
+	if (timer_pending(&group->poll_timer))
 		return;
 
 	rcu_read_lock();
 
-	kworker = rcu_dereference(group->poll_kworker);
+	task = rcu_dereference(group->poll_task);
 	/*
 	 * kworker might be NULL in case psi_trigger_destroy races with
 	 * psi_task_change (hotpath) which can't use locks
 	 */
-	if (likely(kworker))
-		kthread_queue_delayed_work(kworker, &group->poll_work, delay);
-	else
-		atomic_set(&group->poll_scheduled, 0);
+	if (likely(task))
+		mod_timer(&group->poll_timer, jiffies + delay);
 
 	rcu_read_unlock();
 }
 
-static void psi_poll_work(struct kthread_work *work)
+static void psi_poll_work(struct psi_group *group)
 {
-	struct kthread_delayed_work *dwork;
-	struct psi_group *group;
 	u32 changed_states;
 	u64 now;
 
-	dwork = container_of(work, struct kthread_delayed_work, work);
-	group = container_of(dwork, struct psi_group, poll_work);
-
-	atomic_set(&group->poll_scheduled, 0);
-
 	mutex_lock(&group->trigger_lock);
 
 	now = sched_clock();
@@ -623,6 +613,35 @@ out:
 	mutex_unlock(&group->trigger_lock);
 }
 
+static int psi_poll_worker(void *data)
+{
+	struct psi_group *group = (struct psi_group *)data;
+	struct sched_param param = {
+		.sched_priority = 1,
+	};
+
+	sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
+
+	while (true) {
+		wait_event_interruptible(group->poll_wait,
+				atomic_cmpxchg(&group->poll_wakeup, 1, 0) ||
+				kthread_should_stop());
+		if (kthread_should_stop())
+			break;
+
+		psi_poll_work(group);
+	}
+	return 0;
+}
+
+static void poll_timer_fn(struct timer_list *t)
+{
+	struct psi_group *group = from_timer(group, t, poll_timer);
+
+	atomic_set(&group->poll_wakeup, 1);
+	wake_up_interruptible(&group->poll_wait);
+}
+
 static void record_times(struct psi_group_cpu *groupc, int cpu,
 			 bool memstall_tick)
 {
@@ -1099,22 +1118,20 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 
 	mutex_lock(&group->trigger_lock);
 
-	if (!rcu_access_pointer(group->poll_kworker)) {
-		struct sched_param param = {
-			.sched_priority = 1,
-		};
-		struct kthread_worker *kworker;
+	if (!rcu_access_pointer(group->poll_task)) {
+		struct task_struct *task;
 
-		kworker = kthread_create_worker(0, "psimon");
-		if (IS_ERR(kworker)) {
+		task = kthread_create(psi_poll_worker, group, "psimon");
+		if (IS_ERR(task)) {
 			kfree(t);
 			mutex_unlock(&group->trigger_lock);
-			return ERR_CAST(kworker);
+			return ERR_CAST(task);
 		}
-		sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
-		kthread_init_delayed_work(&group->poll_work,
-				psi_poll_work);
-		rcu_assign_pointer(group->poll_kworker, kworker);
+		atomic_set(&group->poll_wakeup, 0);
+		init_waitqueue_head(&group->poll_wait);
+		wake_up_process(task);
+		timer_setup(&group->poll_timer, poll_timer_fn, 0);
+		rcu_assign_pointer(group->poll_task, task);
 	}
 
 	list_add(&t->node, &group->triggers);
@@ -1132,7 +1149,7 @@ static void psi_trigger_destroy(struct kref *ref)
 {
 	struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount);
 	struct psi_group *group = t->group;
-	struct kthread_worker *kworker_to_destroy = NULL;
+	struct task_struct *task_to_destroy = NULL;
 
 	if (static_branch_likely(&psi_disabled))
 		return;
@@ -1158,13 +1175,13 @@ static void psi_trigger_destroy(struct kref *ref)
 			period = min(period, div_u64(tmp->win.size,
 					UPDATES_PER_WINDOW));
 		group->poll_min_period = period;
-		/* Destroy poll_kworker when the last trigger is destroyed */
+		/* Destroy poll_task when the last trigger is destroyed */
 		if (group->poll_states == 0) {
 			group->polling_until = 0;
-			kworker_to_destroy = rcu_dereference_protected(
-					group->poll_kworker,
+			task_to_destroy = rcu_dereference_protected(
+					group->poll_task,
 					lockdep_is_held(&group->trigger_lock));
-			rcu_assign_pointer(group->poll_kworker, NULL);
+			rcu_assign_pointer(group->poll_task, NULL);
 		}
 	}
 
@@ -1172,25 +1189,23 @@ static void psi_trigger_destroy(struct kref *ref)
 
 	/*
 	 * Wait for both *trigger_ptr from psi_trigger_replace and
-	 * poll_kworker RCUs to complete their read-side critical sections
-	 * before destroying the trigger and optionally the poll_kworker
+	 * poll_task RCUs to complete their read-side critical sections
+	 * before destroying the trigger and optionally the poll_task
 	 */
 	synchronize_rcu();
 	/*
 	 * Destroy the kworker after releasing trigger_lock to prevent a
 	 * deadlock while waiting for psi_poll_work to acquire trigger_lock
 	 */
-	if (kworker_to_destroy) {
+	if (task_to_destroy) {
 		/*
 		 * After the RCU grace period has expired, the worker
-		 * can no longer be found through group->poll_kworker.
+		 * can no longer be found through group->poll_task.
 		 * But it might have been already scheduled before
 		 * that - deschedule it cleanly before destroying it.
 		 */
-		kthread_cancel_delayed_work_sync(&group->poll_work);
-		atomic_set(&group->poll_scheduled, 0);
-
-		kthread_destroy_worker(kworker_to_destroy);
+		del_timer_sync(&group->poll_timer);
+		kthread_stop(task_to_destroy);
 	}
 	kfree(t);
 }
-- 
cgit v1.2.3


From 9cc5b8656892a72438ee7deb5e80f5be47643b8b Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 27 May 2020 16:29:09 +0200
Subject: isolcpus: Affine unbound kernel threads to housekeeping cpus

This is a kernel enhancement that configures the cpu affinity of kernel
threads via kernel boot option nohz_full=.

When this option is specified, the cpumask is immediately applied upon
kthread launch. This does not affect kernel threads that specify cpu
and node.

This allows CPU isolation (that is not allowing certain threads
to execute on certain CPUs) without using the isolcpus=domain parameter,
making it possible to enable load balancing on such CPUs
during runtime (see kernel-parameters.txt).

Note-1: this is based off on Wind River's patch at
https://github.com/starlingx-staging/stx-integ/blob/master/kernel/kernel-std/centos/patches/affine-compute-kernel-threads.patch

Difference being that this patch is limited to modifying kernel thread
cpumask. Behaviour of other threads can be controlled via cgroups or
sched_setaffinity.

Note-2: Wind River's patch was based off Christoph Lameter's patch at
https://lwn.net/Articles/565932/ with the only difference being
the kernel parameter changed from kthread to kthread_cpus.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200527142909.23372-3-frederic@kernel.org
---
 include/linux/sched/isolation.h | 1 +
 kernel/kthread.c                | 6 ++++--
 kernel/sched/isolation.c        | 3 ++-
 3 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 0fbcbacd1b29..cc9f393e2a70 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -14,6 +14,7 @@ enum hk_flags {
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
 	HK_FLAG_MANAGED_IRQ	= (1 << 7),
+	HK_FLAG_KTHREAD		= (1 << 8),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/kthread.c b/kernel/kthread.c
index b86d37cda109..032b610912b0 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -27,6 +27,7 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/numa.h>
+#include <linux/sched/isolation.h>
 #include <trace/events/sched.h>
 
 
@@ -383,7 +384,8 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 		 * The kernel thread should not inherit these properties.
 		 */
 		sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
-		set_cpus_allowed_ptr(task, cpu_possible_mask);
+		set_cpus_allowed_ptr(task,
+				     housekeeping_cpumask(HK_FLAG_KTHREAD));
 	}
 	kfree(create);
 	return task;
@@ -608,7 +610,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, cpu_possible_mask);
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 808244f3ddd9..5a6ea03f9882 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,7 +140,8 @@ static int __init housekeeping_nohz_full_setup(char *str)
 {
 	unsigned int flags;
 
-	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
+		HK_FLAG_MISC | HK_FLAG_KTHREAD;
 
 	return housekeeping_setup(str, flags);
 }
-- 
cgit v1.2.3


From b4098bfc5efb1fd7ecf40165132a1283aeea3500 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 26 Jul 2019 16:54:10 +0200
Subject: sched/deadline: Impose global limits on sched_attr::sched_period

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20190726161357.397880775@infradead.org
---
 include/linux/sched/sysctl.h |  3 +++
 kernel/sched/deadline.c      | 23 +++++++++++++++++++++--
 kernel/sysctl.c              | 14 ++++++++++++++
 3 files changed, 38 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 660ac49f2b53..24be30a40814 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -61,6 +61,9 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
+extern unsigned int sysctl_sched_dl_period_max;
+extern unsigned int sysctl_sched_dl_period_min;
+
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 504d2f51b0d6..f31964ad9c2e 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2634,6 +2634,14 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_flags = dl_se->flags;
 }
 
+/*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+
 /*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
@@ -2646,6 +2654,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  */
 bool __checkparam_dl(const struct sched_attr *attr)
 {
+	u64 period, max, min;
+
 	/* special dl tasks don't actually use any parameter */
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return true;
@@ -2669,12 +2679,21 @@ bool __checkparam_dl(const struct sched_attr *attr)
 	    attr->sched_period & (1ULL << 63))
 		return false;
 
+	period = attr->sched_period;
+	if (!period)
+		period = attr->sched_deadline;
+
 	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
+	if (period < attr->sched_deadline ||
 	    attr->sched_deadline < attr->sched_runtime)
 		return false;
 
+	max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
+	min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
+
+	if (period < min || period > max)
+		return false;
+
 	return true;
 }
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db1ce7af2563..4aea67d3d552 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1779,6 +1779,20 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rt_handler,
 	},
+	{
+		.procname	= "sched_deadline_period_max_us",
+		.data		= &sysctl_sched_dl_period_max,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "sched_deadline_period_min_us",
+		.data		= &sysctl_sched_dl_period_min,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "sched_rr_timeslice_ms",
 		.data		= &sysctl_sched_rr_timeslice,
-- 
cgit v1.2.3


From 01e377c539ca52a6c753d0fdbe93b3b8fcd66a1c Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 18 Jun 2020 21:08:10 +0200
Subject: sched/core: Remove mmdrop() definition

Commit
   bf2c59fce4074 ("sched/core: Fix illegal RCU from offline CPUs")

introduced a definition for mmdrop() but a a few lines above there is
already mmdrop() defined as static inline.

Remove the newly introduced mmdrop() definition.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200618190810.790211-1-bigeasy@linutronix.de
---
 include/linux/sched/mm.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 480a4d1b7dd8..a98604ea76f1 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,8 +49,6 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
-void mmdrop(struct mm_struct *mm);
-
 /*
  * This has to be called after a get_task_mm()/mmget_not_zero()
  * followed by taking the mmap_lock for writing before modifying the
-- 
cgit v1.2.3


From 9d246053a69196c7c27068870e9b4b66ac536f68 Mon Sep 17 00:00:00 2001
From: Phil Auld <pauld@redhat.com>
Date: Mon, 29 Jun 2020 15:23:03 -0400
Subject: sched: Add a tracepoint to track rq->nr_running

Add a bare tracepoint trace_sched_update_nr_running_tp which tracks
->nr_running CPU's rq. This is used to accurately trace this data and
provide a visualization of scheduler imbalances in, for example, the
form of a heat map.  The tracepoint is accessed by loading an external
kernel module. An example module (forked from Qais' module and including
the pelt related tracepoints) can be found at:

  https://github.com/auldp/tracepoints-helpers.git

A script to turn the trace-cmd report output into a heatmap plot can be
found at:

  https://github.com/jirvoz/plot-nr-running

The tracepoints are added to add_nr_running() and sub_nr_running() which
are in kernel/sched/sched.h. In order to avoid CREATE_TRACE_POINTS in
the header a wrapper call is used and the trace/events/sched.h include
is moved before sched.h in kernel/sched/core.

Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200629192303.GC120228@lorien.usersys.redhat.com
---
 include/linux/sched.h        |  1 +
 include/trace/events/sched.h |  4 ++++
 kernel/sched/core.c          | 13 +++++++++----
 kernel/sched/fair.c          |  8 ++++++--
 kernel/sched/pelt.c          |  2 --
 kernel/sched/sched.h         | 10 ++++++++++
 6 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 683372943093..12b10ce51a08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2044,6 +2044,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq);
 const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq);
 
 int sched_trace_rq_cpu(struct rq *rq);
+int sched_trace_rq_nr_running(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04f9a4c7b0d9..0d5ff0958d48 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -642,6 +642,10 @@ DECLARE_TRACE(sched_util_est_se_tp,
 	TP_PROTO(struct sched_entity *se),
 	TP_ARGS(se));
 
+DECLARE_TRACE(sched_update_nr_running_tp,
+	TP_PROTO(struct rq *rq, int change),
+	TP_ARGS(rq, change));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4cf30e4de653..ff0519551188 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6,6 +6,10 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+#undef CREATE_TRACE_POINTS
+
 #include "sched.h"
 
 #include <linux/nospec.h>
@@ -23,9 +27,6 @@
 #include "pelt.h"
 #include "smp.h"
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/sched.h>
-
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
  * associated with them) to allow external modules to probe them.
@@ -38,6 +39,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -8195,4 +8197,7 @@ const u32 sched_prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-#undef CREATE_TRACE_POINTS
+void call_trace_sched_update_nr_running(struct rq *rq, int count)
+{
+        trace_sched_update_nr_running_tp(rq, count);
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6fab1d17c575..3213cb247aff 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -22,8 +22,6 @@
  */
 #include "sched.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Targeted preemption latency for CPU-bound tasks:
  *
@@ -11296,3 +11294,9 @@ const struct cpumask *sched_trace_rd_span(struct root_domain *rd)
 #endif
 }
 EXPORT_SYMBOL_GPL(sched_trace_rd_span);
+
+int sched_trace_rq_nr_running(struct rq *rq)
+{
+        return rq ? rq->nr_running : -1;
+}
+EXPORT_SYMBOL_GPL(sched_trace_rq_nr_running);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 11bea3b08115..2c613e1cff3a 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -28,8 +28,6 @@
 #include "sched.h"
 #include "pelt.h"
 
-#include <trace/events/sched.h>
-
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1432f608061..65b72e0487bf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -76,6 +76,8 @@
 #include "cpupri.h"
 #include "cpudeadline.h"
 
+#include <trace/events/sched.h>
+
 #ifdef CONFIG_SCHED_DEBUG
 # define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
@@ -97,6 +99,7 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
+extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -1973,6 +1976,9 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 	unsigned prev_nr = rq->nr_running;
 
 	rq->nr_running = prev_nr + count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
 
 #ifdef CONFIG_SMP
 	if (prev_nr < 2 && rq->nr_running >= 2) {
@@ -1987,6 +1993,10 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
 	rq->nr_running -= count;
+	if (trace_sched_update_nr_running_tp_enabled()) {
+		call_trace_sched_update_nr_running(rq, count);
+	}
+
 	/* Check if we still need preemption */
 	sched_update_tick_dependency(rq);
 }
-- 
cgit v1.2.3


From 58877d347b58c9e971112df5eb311c13bb0acb28 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 2 Jul 2020 14:52:11 +0200
Subject: sched: Better document ttwu()

Dave hit the problem fixed by commit:

  b6e13e85829f ("sched/core: Fix ttwu() race")

and failed to understand much of the code involved. Per his request a
few comments to (hopefully) clarify things.

Requested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200702125211.GQ4800@hirez.programming.kicks-ass.net
---
 include/linux/sched.h |  12 ++--
 kernel/sched/core.c   | 188 +++++++++++++++++++++++++++++++++++++++++++-------
 kernel/sched/sched.h  |  10 +++
 3 files changed, 179 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 12b10ce51a08..5033813fecd5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -154,24 +154,24 @@ struct task_group;
  *
  *   for (;;) {
  *	set_current_state(TASK_UNINTERRUPTIBLE);
- *	if (!need_sleep)
- *		break;
+ *	if (CONDITION)
+ *	   break;
  *
  *	schedule();
  *   }
  *   __set_current_state(TASK_RUNNING);
  *
  * If the caller does not need such serialisation (because, for instance, the
- * condition test and condition change and wakeup are under the same lock) then
+ * CONDITION test and condition change and wakeup are under the same lock) then
  * use __set_current_state().
  *
  * The above is typically ordered against the wakeup, which does:
  *
- *   need_sleep = false;
+ *   CONDITION = 1;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * where wake_up_state() executes a full memory barrier before accessing the
- * task state.
+ * where wake_up_state()/try_to_wake_up() executes a full memory barrier before
+ * accessing p->state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 08d02ce26b71..12db8fbd9c97 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -79,6 +79,100 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+
+/*
+ * Serialization rules:
+ *
+ * Lock order:
+ *
+ *   p->pi_lock
+ *     rq->lock
+ *       hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
+ *
+ *  rq1->lock
+ *    rq2->lock  where: rq1 < rq2
+ *
+ * Regular state:
+ *
+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
+ * always looks at the local rq data structures to find the most elegible task
+ * to run next.
+ *
+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
+ * the local CPU to avoid bouncing the runqueue state around [ see
+ * ttwu_queue_wakelist() ]
+ *
+ * Task wakeup, specifically wakeups that involve migration, are horribly
+ * complicated to avoid having to take two rq->locks.
+ *
+ * Special state:
+ *
+ * System-calls and anything external will use task_rq_lock() which acquires
+ * both p->pi_lock and rq->lock. As a consequence the state they change is
+ * stable while holding either lock:
+ *
+ *  - sched_setaffinity()/
+ *    set_cpus_allowed_ptr():	p->cpus_ptr, p->nr_cpus_allowed
+ *  - set_user_nice():		p->se.load, p->*prio
+ *  - __sched_setscheduler():	p->sched_class, p->policy, p->*prio,
+ *				p->se.load, p->rt_priority,
+ *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
+ *  - sched_setnuma():		p->numa_preferred_nid
+ *  - sched_move_task()/
+ *    cpu_cgroup_fork():	p->sched_task_group
+ *  - uclamp_update_active()	p->uclamp*
+ *
+ * p->state <- TASK_*:
+ *
+ *   is changed locklessly using set_current_state(), __set_current_state() or
+ *   set_special_state(), see their respective comments, or by
+ *   try_to_wake_up(). This latter uses p->pi_lock to serialize against
+ *   concurrent self.
+ *
+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
+ *
+ *   is set by activate_task() and cleared by deactivate_task(), under
+ *   rq->lock. Non-zero indicates the task is runnable, the special
+ *   ON_RQ_MIGRATING state is used for migration without holding both
+ *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
+ *
+ * p->on_cpu <- { 0, 1 }:
+ *
+ *   is set by prepare_task() and cleared by finish_task() such that it will be
+ *   set before p is scheduled-in and cleared after p is scheduled-out, both
+ *   under rq->lock. Non-zero indicates the task is running on its CPU.
+ *
+ *   [ The astute reader will observe that it is possible for two tasks on one
+ *     CPU to have ->on_cpu = 1 at the same time. ]
+ *
+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
+ *
+ *  - Don't call set_task_cpu() on a blocked task:
+ *
+ *    We don't care what CPU we're not running on, this simplifies hotplug,
+ *    the CPU assignment of blocked tasks isn't required to be valid.
+ *
+ *  - for try_to_wake_up(), called under p->pi_lock:
+ *
+ *    This allows try_to_wake_up() to only take one rq->lock, see its comment.
+ *
+ *  - for migration called under rq->lock:
+ *    [ see task_on_rq_migrating() in task_rq_lock() ]
+ *
+ *    o move_queued_task()
+ *    o detach_task()
+ *
+ *  - for migration called under double_rq_lock():
+ *
+ *    o __migrate_swap_task()
+ *    o push_rt_task() / pull_rt_task()
+ *    o push_dl_task() / pull_dl_task()
+ *    o dl_task_offline_migration()
+ *
+ */
+
 /*
  * __task_rq_lock - lock the rq @p resides on.
  */
@@ -1543,8 +1637,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
+	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
 
@@ -1552,8 +1645,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 
 	rq_lock(rq, rf);
 	BUG_ON(task_cpu(p) != new_cpu);
-	enqueue_task(rq, p, 0);
-	p->on_rq = TASK_ON_RQ_QUEUED;
+	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
 	return rq;
@@ -2318,12 +2410,31 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 }
 
 /*
- * Called in case the task @p isn't fully descheduled from its runqueue,
- * in this case we must do a remote wakeup. Its a 'light' wakeup though,
- * since all we need to do is flip p->state to TASK_RUNNING, since
- * the task is still ->on_rq.
+ * Consider @p being inside a wait loop:
+ *
+ *   for (;;) {
+ *      set_current_state(TASK_UNINTERRUPTIBLE);
+ *
+ *      if (CONDITION)
+ *         break;
+ *
+ *      schedule();
+ *   }
+ *   __set_current_state(TASK_RUNNING);
+ *
+ * between set_current_state() and schedule(). In this case @p is still
+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
+ * an atomic manner.
+ *
+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
+ * then schedule() must still happen and p->state can be changed to
+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
+ * need to do a full wakeup with enqueue.
+ *
+ * Returns: %true when the wakeup is done,
+ *          %false otherwise.
  */
-static int ttwu_remote(struct task_struct *p, int wake_flags)
+static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -2464,6 +2575,14 @@ static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 
 	return false;
 }
+
+#else /* !CONFIG_SMP */
+
+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
+{
+	return false;
+}
+
 #endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2471,10 +2590,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
-#if defined(CONFIG_SMP)
 	if (ttwu_queue_wakelist(p, cpu, wake_flags))
 		return;
-#endif
 
 	rq_lock(rq, &rf);
 	update_rq_clock(rq);
@@ -2530,8 +2647,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * migration. However the means are completely different as there is no lock
  * chain to provide order. Instead we do:
  *
- *   1) smp_store_release(X->on_cpu, 0)
- *   2) smp_cond_load_acquire(!X->on_cpu)
+ *   1) smp_store_release(X->on_cpu, 0)   -- finish_task()
+ *   2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
  *
  * Example:
  *
@@ -2571,15 +2688,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * @state: the mask of task states that can be woken
  * @wake_flags: wake modifier flags (WF_*)
  *
- * If (@state & @p->state) @p->state = TASK_RUNNING.
+ * Conceptually does:
+ *
+ *   If (@state & @p->state) @p->state = TASK_RUNNING.
  *
  * If the task was not queued/runnable, also place it back on a runqueue.
  *
- * Atomic against schedule() which would dequeue a task, also see
- * set_current_state().
+ * This function is atomic against schedule() which would dequeue the task.
+ *
+ * It issues a full memory barrier before accessing @p->state, see the comment
+ * with set_current_state().
+ *
+ * Uses p->pi_lock to serialize against concurrent wake-ups.
  *
- * This function executes a full memory barrier before accessing the task
- * state; see set_current_state().
+ * Relies on p->pi_lock stabilizing:
+ *  - p->sched_class
+ *  - p->cpus_ptr
+ *  - p->sched_task_group
+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
+ *
+ * Tries really hard to only take one task_rq(p)->lock for performance.
+ * Takes rq->lock in:
+ *  - ttwu_runnable()    -- old rq, unavoidable, see comment there;
+ *  - ttwu_queue()       -- new rq, for enqueue of the task;
+ *  - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
+ *
+ * As a consequence we race really badly with just about everything. See the
+ * many memory barriers and their comments for details.
  *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
@@ -2595,7 +2730,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		/*
 		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
 		 * == smp_processor_id()'. Together this means we can special
-		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
 		 * In particular:
@@ -2616,8 +2751,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
-	 * reordered with p->state check below. This pairs with mb() in
-	 * set_current_state() the waiting thread does.
+	 * reordered with p->state check below. This pairs with smp_store_mb()
+	 * in set_current_state() that the waiting thread does.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
@@ -2652,7 +2787,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -3222,8 +3357,10 @@ static inline void prepare_task(struct task_struct *next)
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
+	 *
+	 * See the ttwu() WF_ON_CPU case and its ordering comment.
 	 */
-	next->on_cpu = 1;
+	WRITE_ONCE(next->on_cpu, 1);
 #endif
 }
 
@@ -3231,8 +3368,9 @@ static inline void finish_task(struct task_struct *prev)
 {
 #ifdef CONFIG_SMP
 	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
+	 * This must be the very last reference to @prev from this CPU. After
+	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
+	 * must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
 	 * In particular, the load of prev->state in finish_task_switch() must
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 65b72e0487bf..9f33c77258ea 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1203,6 +1203,16 @@ struct rq_flags {
 #endif
 };
 
+/*
+ * Lockdep annotation that avoids accidental unlocks; it's like a
+ * sticky/continuous lockdep_assert_held().
+ *
+ * This avoids code that has access to 'struct rq *rq' (basically everything in
+ * the scheduler) from accidentally unlocking the rq if they do not also have a
+ * copy of the (on-stack) 'struct rq_flags rf'.
+ *
+ * Also see Documentation/locking/lockdep-design.rst.
+ */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
 	rf->cookie = lockdep_pin_lock(&rq->lock);
-- 
cgit v1.2.3


From 46132e3ac58cb2ee48051ed80bffc0070ad59b2e Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Wed, 1 Jul 2020 14:34:18 -0400
Subject: sched: nohz: stop passing around unused "ticks" parameter.

The "ticks" parameter was added in commit 0f004f5a696a ("sched: Cure more
NO_HZ load average woes") since calc_global_nohz() was called and needed
the "ticks" argument.

But in commit c308b56b5398 ("sched: Fix nohz load accounting -- again!")
it became unused as the function calc_global_nohz() dropped using "ticks".

Fixes: c308b56b5398 ("sched: Fix nohz load accounting -- again!")
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593628458-32290-1-git-send-email-paul.gortmaker@windriver.com
---
 include/linux/sched/loadavg.h | 2 +-
 kernel/sched/loadavg.c        | 2 +-
 kernel/time/timekeeping.c     | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 4859bea47a7b..83ec54b65e79 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -43,6 +43,6 @@ extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
-extern void calc_global_load(unsigned long ticks);
+extern void calc_global_load(void);
 
 #endif /* _LINUX_SCHED_LOADAVG_H */
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index de22da666ac7..d2a655643a02 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -347,7 +347,7 @@ static inline void calc_global_nohz(void) { }
  *
  * Called from the global timer code.
  */
-void calc_global_load(unsigned long ticks)
+void calc_global_load(void)
 {
 	unsigned long sample_window;
 	long active, delta;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d20d489841c8..63a632f9896c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2193,7 +2193,7 @@ EXPORT_SYMBOL(ktime_get_coarse_ts64);
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	calc_global_load(ticks);
+	calc_global_load();
 }
 
 /**
-- 
cgit v1.2.3


From e0078e2eb8620079d988f150ba02a4ce9b5a946a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 15 Jul 2020 18:30:31 -0700
Subject: linux/sched/mm.h: drop duplicated words in comments

Drop doubled words "to" and "that".

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/927ea8d8-3f6c-9b65-4c2b-63ab4bd59ef1@infradead.org
---
 include/linux/sched/mm.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a98604ea76f1..6be66f52a2ad 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -23,7 +23,7 @@ extern struct mm_struct *mm_alloc(void);
  * will still exist later on and mmget_not_zero() has to be used before
  * accessing it.
  *
- * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * This is a preferred way to pin @mm for a longer/unbounded amount
  * of time.
  *
  * Use mmdrop() to release the reference acquired by mmgrab().
@@ -232,7 +232,7 @@ static inline unsigned int memalloc_noio_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_noio_save call.
  */
 static inline void memalloc_noio_restore(unsigned int flags)
@@ -263,7 +263,7 @@ static inline unsigned int memalloc_nofs_save(void)
  * @flags: Flags to restore.
  *
  * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function.
- * Always make sure that that the given flags is the return value from the
+ * Always make sure that the given flags is the return value from the
  * pairing memalloc_nofs_save call.
  */
 static inline void memalloc_nofs_restore(unsigned int flags)
-- 
cgit v1.2.3


From 25980c7a79af42f2daa73e2f475ebf4cbac8253e Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Sun, 12 Jul 2020 17:59:15 +0100
Subject: arch_topology, sched/core: Cleanup thermal pressure definition

The following commit:

  14533a16c46d ("thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code")

moved the definition of arch_set_thermal_pressure() to sched/core.c, but
kept its declaration in linux/arch_topology.h. When building e.g. an x86
kernel with CONFIG_SCHED_THERMAL_PRESSURE=y, cpufreq_cooling.c ends up
getting the declaration of arch_set_thermal_pressure() from
include/linux/arch_topology.h, which is somewhat awkward.

On top of this, sched/core.c unconditionally defines
o The thermal_pressure percpu variable
o arch_set_thermal_pressure()

while arch_scale_thermal_pressure() does nothing unless redefined by the
architecture.

arch_*() functions are meant to be defined by architectures, so revert the
aforementioned commit and re-implement it in a way that keeps
arch_set_thermal_pressure() architecture-definable, and doesn't define the
thermal pressure percpu variable for kernels that don't need
it (CONFIG_SCHED_THERMAL_PRESSURE=n).

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200712165917.9168-2-valentin.schneider@arm.com
---
 arch/arm/include/asm/topology.h   |  3 ++-
 arch/arm64/include/asm/topology.h |  3 ++-
 drivers/base/arch_topology.c      | 11 +++++++++++
 include/linux/arch_topology.h     |  4 ++--
 include/linux/sched/topology.h    |  7 +++++++
 kernel/sched/core.c               | 11 -----------
 6 files changed, 24 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 435aba289fc5..e0593cf095d0 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -16,8 +16,9 @@
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #else
 
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 0cc835ddfcd1..e042f6527981 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -34,8 +34,9 @@ void topology_scale_freq_tick(void);
 /* Enable topology flag updates */
 #define arch_update_cpu_topology topology_update_cpu_topology
 
-/* Replace task scheduler's default thermal pressure retrieve API */
+/* Replace task scheduler's default thermal pressure API */
 #define arch_scale_thermal_pressure topology_get_thermal_pressure
+#define arch_set_thermal_pressure   topology_set_thermal_pressure
 
 #include <asm-generic/topology.h>
 
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 4d0a0038b476..75f72d684294 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -54,6 +54,17 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 	per_cpu(cpu_scale, cpu) = capacity;
 }
 
+DEFINE_PER_CPU(unsigned long, thermal_pressure);
+
+void topology_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{
+	int cpu;
+
+	for_each_cpu(cpu, cpus)
+		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
+}
+
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,
 				 char *buf)
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index 0566cb3314ef..69b1dabe39dc 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -39,8 +39,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu)
 	return per_cpu(thermal_pressure, cpu);
 }
 
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure);
+void topology_set_thermal_pressure(const struct cpumask *cpus,
+				   unsigned long th_pressure);
 
 struct cpu_topology {
 	int thread_id;
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index fb11091129b3..764222d637b7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -232,6 +232,13 @@ unsigned long arch_scale_thermal_pressure(int cpu)
 }
 #endif
 
+#ifndef arch_set_thermal_pressure
+static __always_inline
+void arch_set_thermal_pressure(const struct cpumask *cpus,
+			       unsigned long th_pressure)
+{ }
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 12db8fbd9c97..bd8e5211d31f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3869,17 +3869,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
-DEFINE_PER_CPU(unsigned long, thermal_pressure);
-
-void arch_set_thermal_pressure(struct cpumask *cpus,
-			       unsigned long th_pressure)
-{
-	int cpu;
-
-	for_each_cpu(cpu, cpus)
-		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
-}
-
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
-- 
cgit v1.2.3


From c1b7b8d42b5422627b0a8268416a60748f8d000f Mon Sep 17 00:00:00 2001
From: 王文虎 <wenhu.wang@vivo.com>
Date: Mon, 27 Jul 2020 21:39:51 +0800
Subject: sched: Fix a typo in a comment

Change the comment typo: "direcly" -> "directly".

Signed-off-by: Wang Wenhu <wenhu.wang@vivo.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/AAcAXwBTDSpsKN-5iyIOtaqk.1.1595857191899.Hmail.wenhu.wang@vivo.com
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5033813fecd5..adf0125190d4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -374,7 +374,7 @@ struct util_est {
  * For cfs_rq, they are the aggregated values of all runnable and blocked
  * sched_entities.
  *
- * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU
  * capacity scaling. The scaling is done through the rq_clock_pelt that is used
  * for computing those signals (see update_rq_clock_pelt())
  *
-- 
cgit v1.2.3


From 13685c4a08fca9dd76bf53bfcbadc044ab2a08cb Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@arm.com>
Date: Thu, 16 Jul 2020 12:03:45 +0100
Subject: sched/uclamp: Add a new sysctl to control RT default boost value

RT tasks by default run at the highest capacity/performance level. When
uclamp is selected this default behavior is retained by enforcing the
requested uclamp.min (p->uclamp_req[UCLAMP_MIN]) of the RT tasks to be
uclamp_none(UCLAMP_MAX), which is SCHED_CAPACITY_SCALE; the maximum
value.

This is also referred to as 'the default boost value of RT tasks'.

See commit 1a00d999971c ("sched/uclamp: Set default clamps for RT tasks").

On battery powered devices, it is desired to control this default
(currently hardcoded) behavior at runtime to reduce energy consumed by
RT tasks.

For example, a mobile device manufacturer where big.LITTLE architecture
is dominant, the performance of the little cores varies across SoCs, and
on high end ones the big cores could be too power hungry.

Given the diversity of SoCs, the new knob allows manufactures to tune
the best performance/power for RT tasks for the particular hardware they
run on.

They could opt to further tune the value when the user selects
a different power saving mode or when the device is actively charging.

The runtime aspect of it further helps in creating a single kernel image
that can be run on multiple devices that require different tuning.

Keep in mind that a lot of RT tasks in the system are created by the
kernel. On Android for instance I can see over 50 RT tasks, only
a handful of which created by the Android framework.

To control the default behavior globally by system admins and device
integrator, introduce the new sysctl_sched_uclamp_util_min_rt_default
to change the default boost value of the RT tasks.

I anticipate this to be mostly in the form of modifying the init script
of a particular device.

To avoid polluting the fast path with unnecessary code, the approach
taken is to synchronously do the update by traversing all the existing
tasks in the system. This could race with a concurrent fork(), which is
dealt with by introducing sched_post_fork() function which will ensure
the racy fork will get the right update applied.

Tested on Juno-r2 in combination with the RT capacity awareness [1].
By default an RT task will go to the highest capacity CPU and run at the
maximum frequency, which is particularly energy inefficient on high end
mobile devices because the biggest core[s] are 'huge' and power hungry.

With this patch the RT task can be controlled to run anywhere by
default, and doesn't cause the frequency to be maximum all the time.
Yet any task that really needs to be boosted can easily escape this
default behavior by modifying its requested uclamp.min value
(p->uclamp_req[UCLAMP_MIN]) via sched_setattr() syscall.

[1] 804d402fb6f6: ("sched/rt: Make RT capacity-aware")

Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200716110347.19553-2-qais.yousef@arm.com
---
 include/linux/sched.h        |  10 +++-
 include/linux/sched/sysctl.h |   1 +
 include/linux/sched/task.h   |   1 +
 kernel/fork.c                |   1 +
 kernel/sched/core.c          | 119 ++++++++++++++++++++++++++++++++++++++++---
 kernel/sysctl.c              |   7 +++
 6 files changed, 131 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index adf0125190d4..a6bf77c34687 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -686,9 +686,15 @@ struct task_struct {
 	struct sched_dl_entity		dl;
 
 #ifdef CONFIG_UCLAMP_TASK
-	/* Clamp values requested for a scheduling entity */
+	/*
+	 * Clamp values requested for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp_req[UCLAMP_CNT];
-	/* Effective clamp values used for a scheduling entity */
+	/*
+	 * Effective clamp values used for a scheduling entity.
+	 * Must be updated with task_rq_lock() held.
+	 */
 	struct uclamp_se		uclamp[UCLAMP_CNT];
 #endif
 
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 24be30a40814..3c31ba88aca5 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -67,6 +67,7 @@ extern unsigned int sysctl_sched_dl_period_min;
 #ifdef CONFIG_UCLAMP_TASK
 extern unsigned int sysctl_sched_uclamp_util_min;
 extern unsigned int sysctl_sched_uclamp_util_max;
+extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 #endif
 
 #ifdef CONFIG_CFS_BANDWIDTH
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 38359071236a..e7ddab095baf 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -55,6 +55,7 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
 extern void init_idle(struct task_struct *idle, int cpu);
 
 extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern void sched_post_fork(struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 void __noreturn do_task_dead(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index efc5493203ae..e75c2e41f3d1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2304,6 +2304,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
+	sched_post_fork(p);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e44d83f3e0e6..12e1f3a2cabc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -889,6 +889,23 @@ unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 /* Max allowed maximum utilization */
 unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
+/*
+ * By default RT tasks run at the maximum performance point/capacity of the
+ * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to
+ * SCHED_CAPACITY_SCALE.
+ *
+ * This knob allows admins to change the default behavior when uclamp is being
+ * used. In battery powered devices, particularly, running at the maximum
+ * capacity and frequency will increase energy consumption and shorten the
+ * battery life.
+ *
+ * This knob only affects RT tasks that their uclamp_se->user_defined == false.
+ *
+ * This knob will not override the system default sched_util_clamp_min defined
+ * above.
+ */
+unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
@@ -991,6 +1008,64 @@ unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static void __uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	unsigned int default_util_min;
+	struct uclamp_se *uc_se;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	uc_se = &p->uclamp_req[UCLAMP_MIN];
+
+	/* Only sync if user didn't override the default */
+	if (uc_se->user_defined)
+		return;
+
+	default_util_min = sysctl_sched_uclamp_util_min_rt_default;
+	uclamp_se_set(uc_se, default_util_min, false);
+}
+
+static void uclamp_update_util_min_rt_default(struct task_struct *p)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	if (!rt_task(p))
+		return;
+
+	/* Protect updates to p->uclamp_* */
+	rq = task_rq_lock(p, &rf);
+	__uclamp_update_util_min_rt_default(p);
+	task_rq_unlock(rq, p, &rf);
+}
+
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	for_each_process_thread(g, p)
+		uclamp_update_util_min_rt_default(p);
+	rcu_read_unlock();
+}
+
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -1278,12 +1353,13 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
-	int old_min, old_max;
+	int old_min, old_max, old_min_rt;
 	int result;
 
 	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
+	old_min_rt = sysctl_sched_uclamp_util_min_rt_default;
 
 	result = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (result)
@@ -1292,7 +1368,9 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		goto done;
 
 	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
-	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE	||
+	    sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) {
+
 		result = -EINVAL;
 		goto undo;
 	}
@@ -1313,6 +1391,11 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		uclamp_update_root_tg();
 	}
 
+	if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) {
+		static_branch_enable(&sched_uclamp_used);
+		uclamp_sync_util_min_rt_default();
+	}
+
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
 	 * Otherwise, keep it simple and do just a lazy update at each next
@@ -1324,6 +1407,7 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
+	sysctl_sched_uclamp_util_min_rt_default = old_min_rt;
 done:
 	mutex_unlock(&uclamp_mutex);
 
@@ -1369,17 +1453,20 @@ static void __setscheduler_uclamp(struct task_struct *p,
 	 */
 	for_each_clamp_id(clamp_id) {
 		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
-		unsigned int clamp_value = uclamp_none(clamp_id);
 
 		/* Keep using defined clamps across class changes */
 		if (uc_se->user_defined)
 			continue;
 
-		/* By default, RT tasks always get 100% boost */
+		/*
+		 * RT by default have a 100% boost value that could be modified
+		 * at runtime.
+		 */
 		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
+			__uclamp_update_util_min_rt_default(p);
+		else
+			uclamp_se_set(uc_se, uclamp_none(clamp_id), false);
 
-		uclamp_se_set(uc_se, clamp_value, false);
 	}
 
 	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
@@ -1400,6 +1487,10 @@ static void uclamp_fork(struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * We don't need to hold task_rq_lock() when updating p->uclamp_* here
+	 * as the task is still at its early fork stages.
+	 */
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
 
@@ -1412,6 +1503,11 @@ static void uclamp_fork(struct task_struct *p)
 	}
 }
 
+static void uclamp_post_fork(struct task_struct *p)
+{
+	uclamp_update_util_min_rt_default(p);
+}
+
 static void __init init_uclamp_rq(struct rq *rq)
 {
 	enum uclamp_id clamp_id;
@@ -1462,6 +1558,7 @@ static inline int uclamp_validate(struct task_struct *p,
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr) { }
 static inline void uclamp_fork(struct task_struct *p) { }
+static inline void uclamp_post_fork(struct task_struct *p) { }
 static inline void init_uclamp(void) { }
 #endif /* CONFIG_UCLAMP_TASK */
 
@@ -3205,6 +3302,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
+void sched_post_fork(struct task_struct *p)
+{
+	uclamp_post_fork(p);
+}
+
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
@@ -5724,6 +5826,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		kattr.sched_nice = task_nice(p);
 
 #ifdef CONFIG_UCLAMP_TASK
+	/*
+	 * This could race with another potential updater, but this is fine
+	 * because it'll correctly read the old or the new value. We don't need
+	 * to guarantee who wins the race as long as it doesn't return garbage.
+	 */
 	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
 	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4aea67d3d552..1b4d2dc270a5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1815,6 +1815,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sysctl_sched_uclamp_handler,
 	},
+	{
+		.procname	= "sched_util_clamp_min_rt_default",
+		.data		= &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sched_uclamp_handler,
+	},
 #endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
-- 
cgit v1.2.3


From f4470cdf108f00533e8079b19434e6cb48c17fa3 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Fri, 31 Jul 2020 20:20:14 +0100
Subject: sched: Document arch_scale_*_capacity()

Rather that hide their purpose in some dark, damp corner of Documentation/,
add some documentation to the default implementations.

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200731192016.7484-2-valentin.schneider@arm.com
---
 include/linux/sched/topology.h | 10 ++++++++++
 kernel/sched/sched.h           | 10 ++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 764222d637b7..820511289857 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -217,6 +217,16 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 #endif	/* !CONFIG_SMP */
 
 #ifndef arch_scale_cpu_capacity
+/**
+ * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the CPU scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *             max_perf(cpu)
+ *      ----------------------------- * SCHED_CAPACITY_SCALE
+ *      max(max_perf(c) : c \in CPUs)
+ */
 static __always_inline
 unsigned long arch_scale_cpu_capacity(int cpu)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 296efd30d8c9..3fd283892761 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2049,6 +2049,16 @@ void arch_scale_freq_tick(void)
 #endif
 
 #ifndef arch_scale_freq_capacity
+/**
+ * arch_scale_freq_capacity - get the frequency scale factor of a given CPU.
+ * @cpu: the CPU in question.
+ *
+ * Return: the frequency scale factor normalized against SCHED_CAPACITY_SCALE, i.e.
+ *
+ *     f_curr
+ *     ------ * SCHED_CAPACITY_SCALE
+ *     f_max
+ */
 static __always_inline
 unsigned long arch_scale_freq_capacity(int cpu)
 {
-- 
cgit v1.2.3