Add a deadline server for sched_ext tasks

index c509f2e7d69de..71b58a25e2a91 100644
@@ -3644,6 +3644,9 @@ static void __dl_clear_params(struct sched_dl_entity *dl_se)
 	dl_se->dl_non_contending	= 0;
 	dl_se->dl_overrun		= 0;
 	dl_se->dl_server		= 0;
+	dl_se->dl_defer			= 0;
+	dl_se->dl_defer_running		= 0;
+	dl_se->dl_defer_armed		= 0;
 
 #ifdef CONFIG_RT_MUTEXES
 	dl_se->pi_se			= dl_se;

index 41caa22e0680a..93f009e1076d8 100644
@@ -345,8 +345,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct rq *rq = cpu_rq(cpu);
 	u64 runtime, period;
+	int retval = 0;
 	size_t err;
-	int retval;
 	u64 value;
 
 	err = kstrtoull_from_user(ubuf, cnt, 10, &value);

@@ -380,8 +380,6 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		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",

@@ -389,6 +387,9 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 
 		if (rq->cfs.h_nr_queued)
 			dl_server_start(&rq->fair_server);
+
+		if (retval < 0)
+			return retval;
 	}
 
 	*ppos += cnt;

index 93f009e1076d8..dd793f8f3858a 100644
@@ -354,6 +354,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		return err;
 
 	scoped_guard (rq_lock_irqsave, rq) {
+		bool is_active;
+
 		runtime  = rq->fair_server.dl_runtime;
 		period = rq->fair_server.dl_period;
 

@@ -376,8 +378,11 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		update_rq_clock(rq);
-		dl_server_stop(&rq->fair_server);
+		is_active = dl_server_active(&rq->fair_server);
+		if (is_active) {
+			update_rq_clock(rq);
+			dl_server_stop(&rq->fair_server);
+		}
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
 

@@ -385,7 +390,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
 					cpu_of(rq));
 
-		if (rq->cfs.h_nr_queued)
+		if (is_active && runtime)
 			dl_server_start(&rq->fair_server);
 
 		if (retval < 0)

index 045f83ad261e2..88476d8b4e3d2 100644
@@ -8477,6 +8477,9 @@ int sched_cpu_dying(unsigned int cpu)
 		dump_rq_tasks(rq, KERN_WARNING);
 	}
 	dl_server_stop(&rq->fair_server);
+#ifdef CONFIG_SCHED_CLASS_EXT
+	dl_server_stop(&rq->ext_server);
+#endif
 	rq_unlock_irqrestore(rq, &rf);
 
 	calc_load_migrate(rq);

@@ -8680,6 +8683,9 @@ void __init sched_init(void)
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 		fair_server_init(rq);
+#ifdef CONFIG_SCHED_CLASS_EXT
+		ext_server_init(rq);
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 		rq->core = rq;

152 lines not on this page · raw message

index afe28c04d5aa7..809f774183202 100644
@@ -958,6 +958,8 @@ static void update_curr_scx(struct rq *rq)
 		if (!curr->scx.slice)
 			touch_core_sched(rq, curr);
 	}
+
+	dl_server_update(&rq->ext_server, delta_exec);
 }
 
 static bool scx_dsq_priq_less(struct rb_node *node_a,

@@ -1501,6 +1503,10 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags
 	if (enq_flags & SCX_ENQ_WAKEUP)
 		touch_core_sched(rq, p);
 
+	/* Start dl_server if this is the first task being enqueued */
+	if (rq->scx.nr_running == 1)
+		dl_server_start(&rq->ext_server);
+
 	do_enqueue_task(rq, p, enq_flags, sticky_cpu);
 out:
 	rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;

@@ -2512,6 +2518,33 @@ static struct task_struct *pick_task_scx(struct rq *rq, struct rq_flags *rf)
 	return do_pick_task_scx(rq, rf, false);
 }
 
+/*
+ * Select the next task to run from the ext scheduling class.
+ *
+ * Use do_pick_task_scx() directly with @force_scx enabled, since the
+ * dl_server must always select a sched_ext task.
+ */
+static struct task_struct *
+ext_server_pick_task(struct sched_dl_entity *dl_se, struct rq_flags *rf)
+{
+	if (!scx_enabled())
+		return NULL;
+
+	return do_pick_task_scx(dl_se->rq, rf, true);
+}
+
+/*
+ * Initialize the ext server deadline entity.
+ */
+void ext_server_init(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se = &rq->ext_server;
+
+	init_dl_entity(dl_se);
+
+	dl_server_init(dl_se, rq, ext_server_pick_task);
+}
+
 #ifdef CONFIG_SCHED_CORE
 /**
  * scx_prio_less - Task ordering for core-sched

index c174afe1dd177..53793b9a04185 100644
@@ -530,6 +530,9 @@ static void update_curr_idle(struct rq *rq)
 	se->exec_start = now;
 
 	dl_server_update_idle(&rq->fair_server, delta_exec);
+#ifdef CONFIG_SCHED_CLASS_EXT
+	dl_server_update_idle(&rq->ext_server, delta_exec);
+#endif
 }
 
 /*

index 93fce4bbff5ea..d630f46325379 100644
@@ -414,6 +414,7 @@ extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 extern void sched_init_dl_servers(void);
 
 extern void fair_server_init(struct rq *rq);
+extern void ext_server_init(struct rq *rq);
 extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
 extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
 		    u64 runtime, u64 period, bool init);

@@ -1151,6 +1152,7 @@ struct rq {
 	struct dl_rq		dl;
 #ifdef CONFIG_SCHED_CLASS_EXT
 	struct scx_rq		scx;
+	struct sched_dl_entity	ext_server;
 #endif
 
 	struct sched_dl_entity	fair_server;

index cf643a5ddedd2..ac268da917781 100644
@@ -508,6 +508,11 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (rq->fair_server.dl_server)
 		__dl_server_attach_root(&rq->fair_server, rq);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (rq->ext_server.dl_server)
+		__dl_server_attach_root(&rq->ext_server, rq);
+#endif
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)

index dd793f8f3858a..2e9896668c6fd 100644
@@ -336,14 +336,16 @@ enum dl_param {
 	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 unsigned long dl_server_period_max = (1UL << 22) * NSEC_PER_USEC; /* ~4 seconds */
+static unsigned long dl_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)
+static ssize_t sched_server_write_common(struct file *filp, const char __user *ubuf,
+					 size_t cnt, loff_t *ppos, enum dl_param param,
+					 void *server)
 {
 	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
 	struct rq *rq = cpu_rq(cpu);
+	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;
 	u64 runtime, period;
 	int retval = 0;
 	size_t err;

@@ -356,8 +358,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	scoped_guard (rq_lock_irqsave, rq) {
 		bool is_active;
 
-		runtime  = rq->fair_server.dl_runtime;
-		period = rq->fair_server.dl_period;
+		runtime = dl_se->dl_runtime;
+		period = dl_se->dl_period;
 
 		switch (param) {
 		case DL_RUNTIME:

@@ -373,25 +375,25 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 		}
 
 		if (runtime > period ||
-		    period > fair_server_period_max ||
-		    period < fair_server_period_min) {
+		    period > dl_server_period_max ||
+		    period < dl_server_period_min) {
 			return  -EINVAL;
 		}
 
-		is_active = dl_server_active(&rq->fair_server);
+		is_active = dl_server_active(dl_se);
 		if (is_active) {
 			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
+			dl_server_stop(dl_se);
 		}
 
-		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
+		retval = dl_server_apply_params(dl_se, runtime, period, 0);
 
 		if (!runtime)
-			printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n",
-					cpu_of(rq));
+			printk_deferred("%s server disabled in CPU %d, system may crash due to starvation.\n",
+					server == &rq->fair_server ? "Fair" : "Ext", cpu_of(rq));
 
 		if (is_active && runtime)
-			dl_server_start(&rq->fair_server);
+			dl_server_start(dl_se);
 
 		if (retval < 0)
 			return retval;

@@ -401,36 +403,42 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 	return cnt;
 }
 
-static size_t sched_fair_server_show(struct seq_file *m, void *v, enum dl_param param)
+static size_t sched_server_show_common(struct seq_file *m, void *v, enum dl_param param,
+				       void *server)
 {
-	unsigned long cpu = (unsigned long) m->private;
-	struct rq *rq = cpu_rq(cpu);
+	struct sched_dl_entity *dl_se = (struct sched_dl_entity *)server;
 	u64 value;
 
 	switch (param) {
 	case DL_RUNTIME:
-		value = rq->fair_server.dl_runtime;
+		value = dl_se->dl_runtime;
 		break;
 	case DL_PERIOD:
-		value = rq->fair_server.dl_period;
+		value = dl_se->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);
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_RUNTIME,
+					&rq->fair_server);
 }
 
 static int sched_fair_server_runtime_show(struct seq_file *m, void *v)
 {
-	return sched_fair_server_show(m, v, DL_RUNTIME);
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_RUNTIME, &rq->fair_server);
 }
 
 static int sched_fair_server_runtime_open(struct inode *inode, struct file *filp)

@@ -446,16 +454,57 @@ static const struct file_operations fair_server_runtime_fops = {
 	.release	= single_release,
 };
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+static ssize_t
+sched_ext_server_runtime_write(struct file *filp, const char __user *ubuf,
+			       size_t cnt, loff_t *ppos)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_RUNTIME,
+					&rq->ext_server);
+}
+
+static int sched_ext_server_runtime_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_RUNTIME, &rq->ext_server);
+}
+
+static int sched_ext_server_runtime_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_ext_server_runtime_show, inode->i_private);
+}
+
+static const struct file_operations ext_server_runtime_fops = {
+	.open		= sched_ext_server_runtime_open,
+	.write		= sched_ext_server_runtime_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
 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);
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD,
+					&rq->fair_server);
 }
 
 static int sched_fair_server_period_show(struct seq_file *m, void *v)
 {
-	return sched_fair_server_show(m, v, DL_PERIOD);
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_PERIOD, &rq->fair_server);
 }
 
 static int sched_fair_server_period_open(struct inode *inode, struct file *filp)

@@ -471,6 +520,40 @@ static const struct file_operations fair_server_period_fops = {
 	.release	= single_release,
 };
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+static ssize_t
+sched_ext_server_period_write(struct file *filp, const char __user *ubuf,
+			      size_t cnt, loff_t *ppos)
+{
+	long cpu = (long) ((struct seq_file *) filp->private_data)->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_write_common(filp, ubuf, cnt, ppos, DL_PERIOD,
+					&rq->ext_server);
+}
+
+static int sched_ext_server_period_show(struct seq_file *m, void *v)
+{
+	unsigned long cpu = (unsigned long) m->private;
+	struct rq *rq = cpu_rq(cpu);
+
+	return sched_server_show_common(m, v, DL_PERIOD, &rq->ext_server);
+}
+
+static int sched_ext_server_period_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_ext_server_period_show, inode->i_private);
+}
+
+static const struct file_operations ext_server_period_fops = {
+	.open		= sched_ext_server_period_open,
+	.write		= sched_ext_server_period_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
 static struct dentry *debugfs_sched;
 
 static void debugfs_fair_server_init(void)

@@ -494,6 +577,29 @@ static void debugfs_fair_server_init(void)
 	}
 }
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+static void debugfs_ext_server_init(void)
+{
+	struct dentry *d_ext;
+	unsigned long cpu;
+
+	d_ext = debugfs_create_dir("ext_server", debugfs_sched);
+	if (!d_ext)
+		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_ext);
+
+		debugfs_create_file("runtime", 0644, d_cpu, (void *) cpu, &ext_server_runtime_fops);
+		debugfs_create_file("period", 0644, d_cpu, (void *) cpu, &ext_server_period_fops);
+	}
+}
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
 static __init int sched_init_debug(void)
 {
 	struct dentry __maybe_unused *numa;

@@ -532,6 +638,9 @@ static __init int sched_init_debug(void)
 	debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
 
 	debugfs_fair_server_init();
+#ifdef CONFIG_SCHED_CLASS_EXT
+	debugfs_ext_server_init();
+#endif
 
 	return 0;
 }

new file mode 100644
index 0000000000000..80086779dd1eb
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that verified if RT tasks can stall SCHED_EXT tasks.
+ *
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops rt_stall_ops = {
+	.exit			= (void *)rt_stall_exit,
+	.name			= "rt_stall",
+};

240 lines not on this page · raw message

281 lines not on this page · raw message