1 files changed, 341 insertions, 16 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 22f6748c16f6..7f5ffc878411 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -355,8 +355,9 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 static void __hrtick_restart(struct rq *rq)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
+	ktime_t time = rq->hrtick_time;
 
-	hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
+	hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
 }
 
 /*
@@ -380,7 +381,6 @@ static void __hrtick_start(void *arg)
 void hrtick_start(struct rq *rq, u64 delay)
 {
 	struct hrtimer *timer = &rq->hrtick_timer;
-	ktime_t time;
 	s64 delta;
 
 	/*
@@ -388,9 +388,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	 * doesn't make sense and can cause timer DoS.
 	 */
 	delta = max_t(s64, delay, 10000LL);
-	time = ktime_add_ns(timer->base->get_time(), delta);
-
-	hrtimer_set_expires(timer, time);
+	rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
 
 	if (rq == this_rq())
 		__hrtick_restart(rq);
@@ -4970,7 +4968,7 @@ static void __sched notrace __schedule(bool preempt)
 
 	schedule_debug(prev, preempt);
 
-	if (sched_feat(HRTICK))
+	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
@@ -5264,6 +5262,12 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
+#endif
+
+
 /**
  * preempt_schedule_notrace - preempt_schedule called by tracing
  *
@@ -5316,8 +5320,197 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
+#endif
+
 #endif /* CONFIG_PREEMPTION */
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+#include <linux/entry-common.h>
+
+/*
+ * SC:cond_resched
+ * SC:might_resched
+ * SC:preempt_schedule
+ * SC:preempt_schedule_notrace
+ * SC:irqentry_exit_cond_resched
+ *
+ *
+ * NONE:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * VOLUNTARY:
+ *   cond_resched               <- __cond_resched
+ *   might_resched              <- __cond_resched
+ *   preempt_schedule           <- NOP
+ *   preempt_schedule_notrace   <- NOP
+ *   irqentry_exit_cond_resched <- NOP
+ *
+ * FULL:
+ *   cond_resched               <- RET0
+ *   might_resched              <- RET0
+ *   preempt_schedule           <- preempt_schedule
+ *   preempt_schedule_notrace   <- preempt_schedule_notrace
+ *   irqentry_exit_cond_resched <- irqentry_exit_cond_resched
+ */
+
+enum {
+	preempt_dynamic_none = 0,
+	preempt_dynamic_voluntary,
+	preempt_dynamic_full,
+};
+
+static int preempt_dynamic_mode = preempt_dynamic_full;
+
+static int sched_dynamic_mode(const char *str)
+{
+	if (!strcmp(str, "none"))
+		return 0;
+
+	if (!strcmp(str, "voluntary"))
+		return 1;
+
+	if (!strcmp(str, "full"))
+		return 2;
+
+	return -1;
+}
+
+static void sched_dynamic_update(int mode)
+{
+	/*
+	 * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
+	 * the ZERO state, which is invalid.
+	 */
+	static_call_update(cond_resched, __cond_resched);
+	static_call_update(might_resched, __cond_resched);
+	static_call_update(preempt_schedule, __preempt_schedule_func);
+	static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+	static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+
+	switch (mode) {
+	case preempt_dynamic_none:
+		static_call_update(cond_resched, __cond_resched);
+		static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
+		static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
+		static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
+		pr_info("Dynamic Preempt: none\n");
+		break;
+
+	case preempt_dynamic_voluntary:
+		static_call_update(cond_resched, __cond_resched);
+		static_call_update(might_resched, __cond_resched);
+		static_call_update(preempt_schedule, (typeof(&preempt_schedule)) NULL);
+		static_call_update(preempt_schedule_notrace, (typeof(&preempt_schedule_notrace)) NULL);
+		static_call_update(irqentry_exit_cond_resched, (typeof(&irqentry_exit_cond_resched)) NULL);
+		pr_info("Dynamic Preempt: voluntary\n");
+		break;
+
+	case preempt_dynamic_full:
+		static_call_update(cond_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(might_resched, (typeof(&__cond_resched)) __static_call_return0);
+		static_call_update(preempt_schedule, __preempt_schedule_func);
+		static_call_update(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+		static_call_update(irqentry_exit_cond_resched, irqentry_exit_cond_resched);
+		pr_info("Dynamic Preempt: full\n");
+		break;
+	}
+
+	preempt_dynamic_mode = mode;
+}
+
+static int __init setup_preempt_mode(char *str)
+{
+	int mode = sched_dynamic_mode(str);
+	if (mode < 0) {
+		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
+		return 1;
+	}
+
+	sched_dynamic_update(mode);
+	return 0;
+}
+__setup("preempt=", setup_preempt_mode);
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static ssize_t sched_dynamic_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *ppos)
+{
+	char buf[16];
+	int mode;
+
+	if (cnt > 15)
+		cnt = 15;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+	mode = sched_dynamic_mode(strstrip(buf));
+	if (mode < 0)
+		return mode;
+
+	sched_dynamic_update(mode);
+
+	*ppos += cnt;
+
+	return cnt;
+}
+
+static int sched_dynamic_show(struct seq_file *m, void *v)
+{
+	static const char * preempt_modes[] = {
+		"none", "voluntary", "full"
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(preempt_modes); i++) {
+		if (preempt_dynamic_mode == i)
+			seq_puts(m, "(");
+		seq_puts(m, preempt_modes[i]);
+		if (preempt_dynamic_mode == i)
+			seq_puts(m, ")");
+
+		seq_puts(m, " ");
+	}
+
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static int sched_dynamic_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_dynamic_show, NULL);
+}
+
+static const struct file_operations sched_dynamic_fops = {
+	.open		= sched_dynamic_open,
+	.write		= sched_dynamic_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static __init int sched_init_debug_dynamic(void)
+{
+	debugfs_create_file("sched_preempt", 0644, NULL, NULL, &sched_dynamic_fops);
+	return 0;
+}
+late_initcall(sched_init_debug_dynamic);
+
+#endif /* CONFIG_SCHED_DEBUG */
+#endif /* CONFIG_PREEMPT_DYNAMIC */
+
+
 /*
  * This is the entry point to schedule() from kernel preemption
  * off of irq context.
@@ -5615,8 +5808,12 @@ SYSCALL_DEFINE1(nice, int, increment)
  * @p: the task in question.
  *
  * Return: The priority value as seen by users in /proc.
- * RT tasks are offset by -200. Normal tasks are centered
- * around 0, value goes from -16 to +15.
+ *
+ * sched policy         return value   kernel prio    user prio/nice
+ *
+ * normal, batch, idle     [0 ... 39]  [100 ... 139]          0/[-20 ... 19]
+ * fifo, rr             [-2 ... -100]     [98 ... 0]  [1 ... 99]
+ * deadline                     -101             -1           0
  */
 int task_prio(const struct task_struct *p)
 {
@@ -5675,6 +5872,120 @@ struct task_struct *idle_task(int cpu)
 	return cpu_rq(cpu)->idle;
 }
 
+#ifdef CONFIG_SMP
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum cpu_util_type type,
+				 struct task_struct *p)
+{
+	unsigned long dl_util, util, irq;
+	struct rq *rq = cpu_rq(cpu);
+
+	if (!uclamp_is_used() &&
+	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
+		return max;
+	}
+
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= max))
+		return max;
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 *
+	 * CFS and RT utilization can be boosted or capped, depending on
+	 * utilization clamp constraints requested by currently RUNNABLE
+	 * tasks.
+	 * When there are no CFS RUNNABLE tasks, clamps are released and
+	 * frequency will be gracefully reduced with the utilization decay.
+	 */
+	util = util_cfs + cpu_util_rt(rq);
+	if (type == FREQUENCY_UTIL)
+		util = uclamp_rq_util_with(rq, util, p);
+
+	dl_util = cpu_util_dl(rq);
+
+	/*
+	 * For frequency selection we do not make cpu_util_dl() a permanent part
+	 * of this sum because we want to use cpu_bw_dl() later on, but we need
+	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
+	 * that we select f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
+	 */
+	if (util + dl_util >= max)
+		return max;
+
+	/*
+	 * OTOH, for energy computation we need the estimated running time, so
+	 * include util_dl and ignore dl_bw.
+	 */
+	if (type == ENERGY_UTIL)
+		util += dl_util;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              max - irq
+	 *   U' = irq + --------- * U
+	 *                 max
+	 */
+	util = scale_irq_capacity(util, irq, max);
+	util += irq;
+
+	/*
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
+	 * periods of time.
+	 *
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
+	 */
+	if (type == FREQUENCY_UTIL)
+		util += cpu_bw_dl(rq);
+
+	return min(max, util);
+}
+
+unsigned long sched_cpu_util(int cpu, unsigned long max)
+{
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu_rq(cpu)), max,
+				  ENERGY_UTIL, NULL);
+}
+#endif /* CONFIG_SMP */
+
 /**
  * find_process_by_pid - find a process with a matching PID value.
  * @pid: the pid in question.
@@ -5796,11 +6107,10 @@ recheck:
 
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
-	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
+	 * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL,
 	 * SCHED_BATCH and SCHED_IDLE is 0.
 	 */
-	if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
-	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
+	if (attr->sched_priority > MAX_RT_PRIO-1)
 		return -EINVAL;
 	if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
 	    (rt_policy(policy) != (attr->sched_priority != 0)))
@@ -6667,17 +6977,27 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
-#ifndef CONFIG_PREEMPTION
-int __sched _cond_resched(void)
+#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
+int __sched __cond_resched(void)
 {
 	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
+#ifndef CONFIG_PREEMPT_RCU
 	rcu_all_qs();
+#endif
 	return 0;
 }
-EXPORT_SYMBOL(_cond_resched);
+EXPORT_SYMBOL(__cond_resched);
+#endif
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
+EXPORT_STATIC_CALL_TRAMP(cond_resched);
+
+DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
+EXPORT_STATIC_CALL_TRAMP(might_resched);
 #endif
 
 /*
@@ -6868,7 +7188,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 	switch (policy) {
 	case SCHED_FIFO:
 	case SCHED_RR:
-		ret = MAX_USER_RT_PRIO-1;
+		ret = MAX_RT_PRIO-1;
 		break;
 	case SCHED_DEADLINE:
 	case SCHED_NORMAL:
@@ -7508,6 +7828,12 @@ int sched_cpu_deactivate(unsigned int cpu)
 	struct rq_flags rf;
 	int ret;
 
+	/*
+	 * Remove CPU from nohz.idle_cpus_mask to prevent participating in
+	 * load balancing when not active
+	 */
+	nohz_balance_exit_idle(rq);
+
 	set_cpu_active(cpu, false);
 
 	/*
@@ -7652,7 +7978,6 @@ int sched_cpu_dying(unsigned int cpu)
 
 	calc_load_migrate(rq);
 	update_max_interval();
-	nohz_balance_exit_idle(rq);
 	hrtick_clear(rq);
 	return 0;
 }