6 files changed, 65 insertions, 35 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4a0e7b449b88..8471a0f7eb32 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5496,6 +5496,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  *
+ * Use sched_set_fifo(), read its comment.
+ *
  * Return: 0 on success. An error code otherwise.
  *
  * NOTE that the task may be already dead.
@@ -5505,13 +5507,11 @@ int sched_setscheduler(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, true);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler);
 
 int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
 {
 	return __sched_setscheduler(p, attr, true, true);
 }
-EXPORT_SYMBOL_GPL(sched_setattr);
 
 int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
 {
@@ -5536,7 +5536,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	return _sched_setscheduler(p, policy, param, false);
 }
-EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck);
+
+/*
+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
+ * incapable of resource management, which is the one thing an OS really should
+ * be doing.
+ *
+ * This is of course the reason it is limited to privileged users only.
+ *
+ * Worse still; it is fundamentally impossible to compose static priority
+ * workloads. You cannot take two correctly working static prio workloads
+ * and smash them together and still expect them to work.
+ *
+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
+ *
+ *   MAX_RT_PRIO / 2
+ *
+ * The administrator _MUST_ configure the system, the kernel simply doesn't
+ * know enough information to make a sensible choice.
+ */
+void sched_set_fifo(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo);
+
+/*
+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
+ */
+void sched_set_fifo_low(struct task_struct *p)
+{
+	struct sched_param sp = { .sched_priority = 1 };
+	WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
+
+void sched_set_normal(struct task_struct *p, int nice)
+{
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+		.sched_nice = nice,
+	};
+	WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
+}
+EXPORT_SYMBOL_GPL(sched_set_normal);
 
 static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
@@ -6387,10 +6431,10 @@ void sched_show_task(struct task_struct *p)
 	if (!try_get_task_stack(p))
 		return;
 
-	printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));
+	pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
 
 	if (p->state == TASK_RUNNING)
-		printk(KERN_CONT "  running task    ");
+		pr_cont("  running task    ");
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
@@ -6399,8 +6443,8 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
-		task_pid_nr(p), ppid,
+	pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
+		free, task_pid_nr(p), ppid,
 		(unsigned long)task_thread_info(p)->flags);
 
 	print_worker_info(KERN_INFO, p);
@@ -6435,13 +6479,6 @@ void show_state_filter(unsigned long state_filter)
 {
 	struct task_struct *g, *p;
 
-#if BITS_PER_LONG == 32
-	printk(KERN_INFO
-		"  task                PC stack   pid father\n");
-#else
-	printk(KERN_INFO
-		"  task                        PC stack   pid father\n");
-#endif
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
 		/*
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index dc6835bc6490..e39008242cf4 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -909,11 +909,7 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 }
 #endif
 
-static int __init sugov_register(void)
-{
-	return cpufreq_register_governor(&schedutil_gov);
-}
-core_initcall(sugov_register);
+cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
 extern bool sched_energy_update;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2ba8f230feb9..1a68a0536add 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6509,7 +6509,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
 		max_util = max(max_util, cpu_util);
 	}
 
-	return em_pd_energy(pd->em_pd, max_util, sum_util);
+	return em_cpu_energy(pd->em_pd, max_util, sum_util);
 }
 
 /*
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index e53b711bd643..967732c0766c 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -616,11 +616,8 @@ out:
 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);
+	sched_set_fifo_low(current);
 
 	while (true) {
 		wait_event_interruptible(group->poll_wait,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3fd283892761..28709f6b0975 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1999,7 +1999,7 @@ 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);
+		call_trace_sched_update_nr_running(rq, -count);
 	}
 
 	/* Check if we still need preemption */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 9079d865a935..007b0a6b0152 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -272,10 +272,10 @@ static void perf_domain_debug(const struct cpumask *cpu_map,
 	printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map));
 
 	while (pd) {
-		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }",
+		printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_pstate=%d }",
 				cpumask_first(perf_domain_span(pd)),
 				cpumask_pr_args(perf_domain_span(pd)),
-				em_pd_nr_cap_states(pd->em_pd));
+				em_pd_nr_perf_states(pd->em_pd));
 		pd = pd->next;
 	}
 
@@ -313,26 +313,26 @@ static void sched_energy_set(bool has_eas)
  *
  * The complexity of the Energy Model is defined as:
  *
- *              C = nr_pd * (nr_cpus + nr_cs)
+ *              C = nr_pd * (nr_cpus + nr_ps)
  *
  * with parameters defined as:
  *  - nr_pd:    the number of performance domains
  *  - nr_cpus:  the number of CPUs
- *  - nr_cs:    the sum of the number of capacity states of all performance
+ *  - nr_ps:    the sum of the number of performance states of all performance
  *              domains (for example, on a system with 2 performance domains,
- *              with 10 capacity states each, nr_cs = 2 * 10 = 20).
+ *              with 10 performance states each, nr_ps = 2 * 10 = 20).
  *
  * It is generally not a good idea to use such a model in the wake-up path on
  * very complex platforms because of the associated scheduling overheads. The
  * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs
- * with per-CPU DVFS and less than 8 capacity states each, for example.
+ * with per-CPU DVFS and less than 8 performance states each, for example.
  */
 #define EM_MAX_COMPLEXITY 2048
 
 extern struct cpufreq_governor schedutil_gov;
 static bool build_perf_domains(const struct cpumask *cpu_map)
 {
-	int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map);
+	int i, nr_pd = 0, nr_ps = 0, nr_cpus = cpumask_weight(cpu_map);
 	struct perf_domain *pd = NULL, *tmp;
 	int cpu = cpumask_first(cpu_map);
 	struct root_domain *rd = cpu_rq(cpu)->rd;
@@ -384,15 +384,15 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		pd = tmp;
 
 		/*
-		 * Count performance domains and capacity states for the
+		 * Count performance domains and performance states for the
 		 * complexity check.
 		 */
 		nr_pd++;
-		nr_cs += em_pd_nr_cap_states(pd->em_pd);
+		nr_ps += em_pd_nr_perf_states(pd->em_pd);
 	}
 
 	/* Bail out if the Energy Model complexity is too high. */
-	if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) {
+	if (nr_pd * (nr_ps + nr_cpus) > EM_MAX_COMPLEXITY) {
 		WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n",
 						cpumask_pr_args(cpu_map));
 		goto free;