Merge tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Implement the SCHED_DEADLINE server infrastructure - Daniel Bristot
   de Oliveira's last major contribution to the kernel:

     "SCHED_DEADLINE servers can help fixing starvation issues of low
      priority tasks (e.g., SCHED_OTHER) when higher priority tasks
      monopolize CPU cycles. Today we have RT Throttling; DEADLINE
      servers should be able to replace and improve that."

   (Daniel Bristot de Oliveira, Peter Zijlstra, Joel Fernandes, Youssef
   Esmat, Huang Shijie)

 - Preparatory changes for sched_ext integration:
     - Use set_next_task(.first) where required
     - Fix up set_next_task() implementations
     - Clean up DL server vs. core sched
     - Split up put_prev_task_balance()
     - Rework pick_next_task()
     - Combine the last put_prev_task() and the first set_next_task()
     - Rework dl_server
     - Add put_prev_task(.next)

   (Peter Zijlstra, with a fix by Tejun Heo)

 - Complete the EEVDF transition and refine EEVDF scheduling:
     - Implement delayed dequeue
     - Allow shorter slices to wakeup-preempt
     - Use sched_attr::sched_runtime to set request/slice suggestion
     - Document the new feature flags
     - Remove unused and duplicate-functionality fields
     - Simplify & unify pick_next_task_fair()
     - Misc debuggability enhancements

   (Peter Zijlstra, with fixes/cleanups by Dietmar Eggemann, Valentin
   Schneider and Chuyi Zhou)

 - Initialize the vruntime of a new task when it is first enqueued,
   resulting in significant decrease in latency of newly woken tasks
   (Zhang Qiao)

 - Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
   (K Prateek Nayak, Peter Zijlstra)

 - Clean up and clarify the usage of Clean up usage of rt_task()
   (Qais Yousef)

 - Preempt SCHED_IDLE entities in strict cgroup hierarchies
   (Tianchen Ding)

 - Clarify the documentation of time units for deadline scheduler
   parameters (Christian Loehle)

 - Remove the HZ_BW chicken-bit feature flag introduced a year ago,
   the original change seems to be working fine (Phil Auld)

 - Misc fixes and cleanups (Chen Yu, Dan Carpenter, Huang Shijie,
   Peilin He, Qais Yousefm and Vincent Guittot)

* tag 'sched-core-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/cpufreq: Use NSEC_PER_MSEC for deadline task
  cpufreq/cppc: Use NSEC_PER_MSEC for deadline task
  sched/deadline: Clarify nanoseconds in uapi
  sched/deadline: Convert schedtool example to chrt
  sched/debug: Fix the runnable tasks output
  sched: Fix sched_delayed vs sched_core
  kernel/sched: Fix util_est accounting for DELAY_DEQUEUE
  kthread: Fix task state in kthread worker if being frozen
  sched/pelt: Use rq_clock_task() for hw_pressure
  sched/fair: Move effective_cpu_util() and effective_cpu_util() in fair.c
  sched/core: Introduce SM_IDLE and an idle re-entry fast-path in __schedule()
  sched: Add put_prev_task(.next)
  sched: Rework dl_server
  sched: Combine the last put_prev_task() and the first set_next_task()
  sched: Rework pick_next_task()
  sched: Split up put_prev_task_balance()
  sched: Clean up DL server vs core sched
  sched: Fixup set_next_task() implementations
  sched: Use set_next_task(.first) where required
  sched/fair: Properly deactivate sched_delayed task upon class change
  ...

1 files changed, 186 insertions, 12 deletions

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index c1eb9a1afd13..de1dc5264b3f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -333,8 +333,165 @@ static const struct file_operations sched_debug_fops = {
 	.release	= seq_release,
 };
 
+enum dl_param {
+	DL_RUNTIME = 0,
+	DL_PERIOD,
+};
+
+static unsigned long fair_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long fair_server_period_min = (100) * NSEC_PER_USEC;     /* 100 us */
+
+static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubuf,
+				       size_t cnt, loff_t *ppos, enum dl_param param)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 runtime, period;
+	size_t err;
+	int retval;
+	u64 value;
+
+	err = kstrtoull_from_user(ubuf, cnt, 10, &value);
+	if (err)
+		return err;
+
+	scoped_guard (rq_lock_irqsave, rq) {
+		runtime  = rq->fair_server.dl_runtime;
+		period = rq->fair_server.dl_period;
+
+		switch (param) {
+		case DL_RUNTIME:
+			if (runtime == value)
+				break;
+			runtime = value;
+			break;
+		case DL_PERIOD:
+			if (value == period)
+				break;
+			period = value;
+			break;
+		}
+
+		if (runtime > period ||
+		    period > fair_server_period_max ||
+		    period < fair_server_period_min) {
+			return  -EINVAL;
+		}
+
+		if (rq->cfs.h_nr_running) {
+			update_rq_clock(rq);
+			dl_server_stop(&rq->fair_server);
+		}
+
+		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
+		if (retval)
+			cnt = retval;
+
+		if (!runtime)
+			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
+					cpu_of(rq));
+
+		if (rq->cfs.h_nr_running)
+			dl_server_start(&rq->fair_server);
+	}
+
+	*ppos += cnt;
+	return cnt;
+}
+
+static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+	u64 value;
+
+	switch (param) {
+	case DL_RUNTIME:
+		value = rq->fair_server.dl_runtime;
+		break;
+	case DL_PERIOD:
+		value = rq->fair_server.dl_period;
+		break;
+	}
+
+	seq_printf(m, "%llu\n", value);
+	return 0;
+
+}
+
+static ssize_t
+sched_fair_server_runtime_write(struct file *filp, const char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_RUNTIME);
+}
+
+static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_runtime_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_runtime_fops = {
+	.open		= sched_fair_server_runtime_open,
+	.write		= sched_fair_server_runtime_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t
+sched_fair_server_period_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	return sched_fair_server_write(filp, ubuf, cnt, ppos, DL_PERIOD);
+}
+
+static int sched_fair_server_period_show(struct seq_file *m, void *v)
+{
+	return sched_fair_server_show(m, v, DL_PERIOD);
+}
+
+static int sched_fair_server_period_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_fair_server_period_show, inode->i_private);
+}
+
+static const struct file_operations fair_server_period_fops = {
+	.open		= sched_fair_server_period_open,
+	.write		= sched_fair_server_period_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static struct dentry *debugfs_sched;
 
+static void debugfs_fair_server_init(void)
+{
+	struct dentry *d_fair;
+	unsigned long cpu;
+
+	d_fair = debugfs_create_dir("fair_server", debugfs_sched);
+	if (!d_fair)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct dentry *d_cpu;
+		char buf[32];
+
+		snprintf(buf, sizeof(buf), "cpu%lu", cpu);
+		d_cpu = debugfs_create_dir(buf, d_fair);
+
+		debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &fair_server_runtime_fops);
+		debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &fair_server_period_fops);
+	}
+}
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;
@@ -374,6 +531,8 @@ static __init int sched_init_debug(void)
 
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
+	debugfs_fair_server_init();
+
 	return 0;
 }
 late_initcall(sched_init_debug);
@@ -580,27 +739,27 @@ 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 %c %9Ld.%06ld %9Ld.%06ld %9Ld.%06ld %9Ld %5d ",
+	SEQ_printf(m, " %15s %5d %9Ld.%06ld   %c   %9Ld.%06ld %c %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),
+		p->se.custom_slice ? 'S' : ' ',
 		SPLIT_NS(p->se.slice),
 		SPLIT_NS(p->se.sum_exec_runtime),
 		(long long)(p->nvcsw + p->nivcsw),
 		p->prio);
 
-	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld",
+	SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld",
 		SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)),
-		SPLIT_NS(p->se.sum_exec_runtime),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)),
 		SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
+	SEQ_printf(m, "   %d      %d", task_node(p), task_numa_group_id(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
-	SEQ_printf_task_group_path(m, task_group(p), " %s")
+	SEQ_printf_task_group_path(m, task_group(p), "        %s")
 #endif
 
 	SEQ_printf(m, "\n");
@@ -612,10 +771,26 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "runnable tasks:\n");
-	SEQ_printf(m, " S            task   PID         tree-key  switches  prio"
-		   "     wait-time             sum-exec        sum-sleep\n");
+	SEQ_printf(m, " S            task   PID       vruntime   eligible    "
+		   "deadline             slice          sum-exec      switches  "
+		   "prio         wait-time        sum-sleep       sum-block"
+#ifdef CONFIG_NUMA_BALANCING
+		   "  node   group-id"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "  group-path"
+#endif
+		   "\n");
 	SEQ_printf(m, "-------------------------------------------------------"
-		   "------------------------------------------------------\n");
+		   "------------------------------------------------------"
+		   "------------------------------------------------------"
+#ifdef CONFIG_NUMA_BALANCING
+		   "--------------"
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+		   "--------------"
+#endif
+		   "\n");
 
 	rcu_read_lock();
 	for_each_process_thread(g, p) {
@@ -641,8 +816,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);
 #endif
-	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
-			SPLIT_NS(cfs_rq->exec_clock));
 
 	raw_spin_rq_lock_irqsave(rq, flags);
 	root = __pick_root_entity(cfs_rq);
@@ -669,8 +842,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			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);
 	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
 	SEQ_printf(m, "  .%-30s: %d\n", "idle_nr_running",
@@ -730,9 +901,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
 	PU(rt_nr_running);
+
+#ifdef CONFIG_RT_GROUP_SCHED
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
+#endif
 
 #undef PN
 #undef PU