[PATCH -rebased 00/15] Add a deadline server for sched_ext tasks

[PATCH -rebased 00/15] Add a deadline server for sched_ext tasks

[Joel Fernandes]

Just rebased on Linus's master and made adjustments. These patches have been
complete for some time without any issues. I am hoping they are merged for 6.18.

sched_ext tasks currently are starved by RT hoggers especially since RT
throttling was replaced by deadline servers to boost only CFS tasks. Several
users in the community have reported issues with RT stalling sched_ext tasks.
Add a sched_ext deadline server as well so that sched_ext tasks are also
boosted and do not suffer starvation.

2 kselftest are provided to verify the starvation fixes and bandwidth
allocation is looking correct.

Previous series:
https://lore.kernel.org/all/20250702232944.3221001-1-joelagnelf@nvidia.com/

Andrea Righi (4):
  sched/deadline: Add support to remove DL server's bandwidth
    contribution
  sched/deadline: Account ext server bandwidth
  sched/deadline: Allow to initialize DL server when needed
  selftests/sched_ext: Add test for sched_ext dl_server

Joel Fernandes (11):
  sched/debug: Fix updating of ppos on server write ops
  sched/debug: Stop and start server based on if it was active
  sched/deadline: Clear the defer params
  sched/deadline: Return EBUSY if dl_bw_cpus is zero
  sched: Add support to pick functions to take rf
  sched: Add a server arg to dl_server_update_idle_time()
  sched_ext: Add a DL server for sched_ext tasks
  sched/debug: Add support to change sched_ext server params
  sched_ext: Selectively enable ext and fair DL servers
  sched/deadline: Fix DL server crash in inactive_timer callback
  selftests/sched_ext: Add test for DL server total_bw consistency

 include/linux/sched.h                         |   2 +-
 kernel/sched/core.c                           |  19 +-
 kernel/sched/deadline.c                       | 144 +++++++--
 kernel/sched/debug.c                          | 161 ++++++++--
 kernel/sched/ext.c                            | 161 +++++++++-
 kernel/sched/fair.c                           |  15 +-
 kernel/sched/idle.c                           |   4 +-
 kernel/sched/rt.c                             |   2 +-
 kernel/sched/sched.h                          |  17 +-
 kernel/sched/stop_task.c                      |   2 +-
 kernel/sched/topology.c                       |   5 +
 tools/testing/selftests/sched_ext/Makefile    |   2 +
 .../selftests/sched_ext/rt_stall.bpf.c        |  23 ++
 tools/testing/selftests/sched_ext/rt_stall.c  | 213 +++++++++++++
 tools/testing/selftests/sched_ext/total_bw.c  | 282 ++++++++++++++++++
 15 files changed, 955 insertions(+), 97 deletions(-)
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c
 create mode 100644 tools/testing/selftests/sched_ext/total_bw.c

-- 
2.34.1

[PATCH -rebased 14/15] selftests/sched_ext: Add test for sched_ext dl_server

[Joel Fernandes]

From: Andrea Righi <arighi@nvidia.com>

Add a selftest to validate the correct behavior of the deadline server
for the ext_sched_class.

[ Joel: Replaced occurences of CFS in the test with EXT. ]

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 tools/testing/selftests/sched_ext/Makefile    |   1 +
 .../selftests/sched_ext/rt_stall.bpf.c        |  23 ++
 tools/testing/selftests/sched_ext/rt_stall.c  | 213 ++++++++++++++++++
 3 files changed, 237 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 9d9d6b4c38b0..f0a8cba3a99f 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -182,6 +182,7 @@ auto-test-targets :=			\
 	select_cpu_dispatch_bad_dsq	\
 	select_cpu_dispatch_dbl_dsp	\
 	select_cpu_vtime		\
+	rt_stall			\
 	test_example			\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
new file mode 100644
index 000000000000..80086779dd1e
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c
@@ -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",
+};
diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c
new file mode 100644
index 000000000000..d4cb545ebfd8
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/rt_stall.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sched.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <linux/sched.h>
+#include <signal.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "rt_stall.bpf.skel.h"
+#include "scx_test.h"
+#include "../kselftest.h"
+
+#define CORE_ID		0	/* CPU to pin tasks to */
+#define RUN_TIME        5	/* How long to run the test in seconds */
+
+/* Simple busy-wait function for test tasks */
+static void process_func(void)
+{
+	while (1) {
+		/* Busy wait */
+		for (volatile unsigned long i = 0; i < 10000000UL; i++);
+	}
+}
+
+/* Set CPU affinity to a specific core */
+static void set_affinity(int cpu)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	if (sched_setaffinity(0, sizeof(mask), &mask) != 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Set task scheduling policy and priority */
+static void set_sched(int policy, int priority)
+{
+	struct sched_param param;
+
+	param.sched_priority = priority;
+	if (sched_setscheduler(0, policy, &param) != 0) {
+		perror("sched_setscheduler");
+		exit(EXIT_FAILURE);
+	}
+}
+
+/* Get process runtime from /proc/<pid>/stat */
+static float get_process_runtime(int pid)
+{
+	char path[256];
+	FILE *file;
+	long utime, stime;
+	int fields;
+
+	snprintf(path, sizeof(path), "/proc/%d/stat", pid);
+	file = fopen(path, "r");
+	if (file == NULL) {
+		perror("Failed to open stat file");
+		return -1;
+	}
+
+	/* Skip the first 13 fields and read the 14th and 15th */
+	fields = fscanf(file,
+			"%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu",
+			&utime, &stime);
+	fclose(file);
+
+	if (fields != 2) {
+		fprintf(stderr, "Failed to read stat file\n");
+		return -1;
+	}
+
+	/* Calculate the total time spent in the process */
+	long total_time = utime + stime;
+	long ticks_per_second = sysconf(_SC_CLK_TCK);
+	float runtime_seconds = total_time * 1.0 / ticks_per_second;
+
+	return runtime_seconds;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct rt_stall *skel;
+
+	skel = rt_stall__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static bool sched_stress_test(void)
+{
+	float cfs_runtime, rt_runtime;
+	int cfs_pid, rt_pid;
+	float expected_min_ratio = 0.04; /* 4% */
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	/* Create and set up a EXT task */
+	cfs_pid = fork();
+	if (cfs_pid == 0) {
+		set_affinity(CORE_ID);
+		process_func();
+		exit(0);
+	} else if (cfs_pid < 0) {
+		perror("fork for EXT task");
+		ksft_exit_fail();
+	}
+
+	/* Create an RT task */
+	rt_pid = fork();
+	if (rt_pid == 0) {
+		set_affinity(CORE_ID);
+		set_sched(SCHED_FIFO, 50);
+		process_func();
+		exit(0);
+	} else if (rt_pid < 0) {
+		perror("fork for RT task");
+		ksft_exit_fail();
+	}
+
+	/* Let the processes run for the specified time */
+	sleep(RUN_TIME);
+
+	/* Get runtime for the EXT task */
+	cfs_runtime = get_process_runtime(cfs_pid);
+	if (cfs_runtime != -1)
+		ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n", cfs_pid, cfs_runtime);
+	else
+		ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid);
+
+	/* Get runtime for the RT task */
+	rt_runtime = get_process_runtime(rt_pid);
+	if (rt_runtime != -1)
+		ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime);
+	else
+		ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid);
+
+	/* Kill the processes */
+	kill(cfs_pid, SIGKILL);
+	kill(rt_pid, SIGKILL);
+	waitpid(cfs_pid, NULL, 0);
+	waitpid(rt_pid, NULL, 0);
+
+	/* Verify that the scx task got enough runtime */
+	float actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime);
+	ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100);
+
+	if (actual_ratio >= expected_min_ratio) {
+		ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n",
+				      expected_min_ratio * 100);
+		return true;
+	} else {
+		ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n",
+				      expected_min_ratio * 100);
+		return false;
+	}
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+	struct bpf_link *link;
+	bool res;
+
+	link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	res = sched_stress_test();
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	if (!res)
+		ksft_exit_fail();
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+
+	rt_stall__destroy(skel);
+}
+
+struct scx_test rt_stall = {
+	.name = "rt_stall",
+	.description = "Verify that RT tasks cannot stall SCHED_EXT tasks",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&rt_stall)
-- 
2.34.1

[PATCH -rebased 15/15] selftests/sched_ext: Add test for DL server total_bw consistency

[Joel Fernandes]

Add a new kselftest to verify that the total_bw value in
/sys/kernel/debug/sched/debug remains consistent across all CPUs
under different sched_ext BPF program states:

1. Before a BPF scheduler is loaded
2. While a BPF scheduler is loaded and active
3. After a BPF scheduler is unloaded

The test runs CPU stress threads to ensure DL server bandwidth
values stabilize before checking consistency. This helps catch
potential issues with DL server bandwidth accounting during
sched_ext transitions.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 tools/testing/selftests/sched_ext/Makefile   |   1 +
 tools/testing/selftests/sched_ext/total_bw.c | 282 +++++++++++++++++++
 2 files changed, 283 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/total_bw.c

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index f0a8cba3a99f..d48be158b0a1 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -184,6 +184,7 @@ auto-test-targets :=			\
 	select_cpu_vtime		\
 	rt_stall			\
 	test_example			\
+	total_bw			\
 
 testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
 
diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c
new file mode 100644
index 000000000000..d70852cee358
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/total_bw.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test to verify that total_bw value remains consistent across all CPUs
+ * in different BPF program states.
+ *
+ * Copyright (C) 2025 Nvidia Corporation.
+ */
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <scx/common.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "minimal.bpf.skel.h"
+#include "scx_test.h"
+
+#define MAX_CPUS 512
+#define STRESS_DURATION_SEC 5
+
+struct total_bw_ctx {
+	struct minimal *skel;
+	long baseline_bw[MAX_CPUS];
+	int nr_cpus;
+};
+
+static void *cpu_stress_thread(void *arg)
+{
+	volatile int i;
+	time_t end_time = time(NULL) + STRESS_DURATION_SEC;
+
+	while (time(NULL) < end_time) {
+		for (i = 0; i < 1000000; i++);
+	}
+
+	return NULL;
+}
+
+/*
+ * The first enqueue on a CPU causes the DL server to start, for that
+ * reason run stressor threads in the hopes it schedules on all CPUs.
+ */
+static int run_cpu_stress(int nr_cpus)
+{
+	pthread_t *threads;
+	int i, ret = 0;
+
+	threads = calloc(nr_cpus, sizeof(pthread_t));
+	if (!threads)
+		return -ENOMEM;
+
+	/* Create threads to run on each CPU */
+	for (i = 0; i < nr_cpus; i++) {
+		if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) {
+			ret = -errno;
+			fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret));
+			break;
+		}
+	}
+
+	/* Wait for all threads to complete */
+	for (i = 0; i < nr_cpus; i++) {
+		if (threads[i])
+			pthread_join(threads[i], NULL);
+	}
+
+	free(threads);
+	return ret;
+}
+
+static int read_total_bw_values(long *bw_values, int max_cpus)
+{
+	FILE *fp;
+	char line[256];
+	int cpu_count = 0;
+
+	fp = fopen("/sys/kernel/debug/sched/debug", "r");
+	if (!fp) {
+		SCX_ERR("Failed to open debug file");
+		return -1;
+	}
+
+	while (fgets(line, sizeof(line), fp)) {
+		char *bw_str = strstr(line, "total_bw");
+		if (bw_str) {
+			bw_str = strchr(bw_str, ':');
+			if (bw_str) {
+				/* Only store up to max_cpus values */
+				if (cpu_count < max_cpus) {
+					bw_values[cpu_count] = atol(bw_str + 1);
+				}
+				cpu_count++;
+			}
+		}
+	}
+
+	fclose(fp);
+	return cpu_count;
+}
+
+static bool verify_total_bw_consistency(long *bw_values, int count)
+{
+	int i;
+	long first_value;
+
+	if (count <= 0)
+		return false;
+
+	first_value = bw_values[0];
+
+	for (i = 1; i < count; i++) {
+		if (bw_values[i] != first_value) {
+			SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld",
+				first_value, i, bw_values[i]);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int fetch_verify_total_bw(long *bw_values, int nr_cpus)
+{
+	int attempts = 0;
+	int max_attempts = 10;
+	int count;
+
+	/*
+	 * The first enqueue on a CPU causes the DL server to start, for that
+	 * reason run stressor threads in the hopes it schedules on all CPUs.
+	 */
+	if (run_cpu_stress(nr_cpus) < 0) {
+		SCX_ERR("Failed to run CPU stress");
+		return -1;
+	}
+
+	/* Try multiple times to get stable values */
+	while (attempts < max_attempts) {
+		count = read_total_bw_values(bw_values, nr_cpus);
+		fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus);
+		/* If system has more CPUs than we're testing, that's OK */
+		if (count < nr_cpus) {
+			SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count);
+			attempts++;
+			sleep(1);
+			continue;
+		}
+
+		/* Only verify the CPUs we're testing */
+		if (verify_total_bw_consistency(bw_values, nr_cpus)) {
+			fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]);
+			return 0;
+		}
+
+		attempts++;
+		sleep(1);
+	}
+
+	return -1;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct total_bw_ctx *test_ctx;
+
+	if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) {
+		fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n");
+		return SCX_TEST_SKIP;
+	}
+
+	test_ctx = calloc(1, sizeof(*test_ctx));
+	if (!test_ctx)
+		return SCX_TEST_FAIL;
+
+	test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (test_ctx->nr_cpus <= 0) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */
+	if (test_ctx->nr_cpus > MAX_CPUS) {
+		test_ctx->nr_cpus = MAX_CPUS;
+	}
+
+	/* Test scenario 1: BPF program not loaded */
+	/* Read and verify baseline total_bw before loading BPF program */
+	fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable baseline values");
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	/* Load the BPF skeleton */
+	test_ctx->skel = minimal__open();
+	if (!test_ctx->skel) {
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	SCX_ENUM_INIT(test_ctx->skel);
+	if (minimal__load(test_ctx->skel)) {
+		minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+		return SCX_TEST_FAIL;
+	}
+
+	*ctx = test_ctx;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+	struct bpf_link *link;
+	long loaded_bw[MAX_CPUS];
+	long unloaded_bw[MAX_CPUS];
+	int i;
+
+	/* Test scenario 2: BPF program loaded */
+	link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	fprintf(stderr, "BPF program loaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values with BPF loaded");
+		bpf_link__destroy(link);
+		return SCX_TEST_FAIL;
+	}
+	bpf_link__destroy(link);
+
+	/* Test scenario 3: BPF program unloaded */
+	fprintf(stderr, "BPF program unloaded, reading total_bw values\n");
+	if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values after BPF unload");
+		return SCX_TEST_FAIL;
+	}
+
+	/* Verify all three scenarios have the same total_bw values */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (test_ctx->baseline_bw[i] != loaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], loaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+
+		if (test_ctx->baseline_bw[i] != unloaded_bw[i]) {
+			SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld",
+				i, test_ctx->baseline_bw[i], unloaded_bw[i]);
+			return SCX_TEST_FAIL;
+		}
+	}
+
+	fprintf(stderr, "All total_bw values are consistent across all scenarios\n");
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct total_bw_ctx *test_ctx = ctx;
+
+	if (test_ctx) {
+		if (test_ctx->skel)
+			minimal__destroy(test_ctx->skel);
+		free(test_ctx);
+	}
+}
+
+struct scx_test total_bw = {
+	.name = "total_bw",
+	.description = "Verify total_bw consistency across BPF program states",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&total_bw)
-- 
2.34.1

Re: [PATCH -rebased 00/15] Add a deadline server for sched_ext tasks

[Juri Lelli]

Hi Joel,

On 09/08/25 14:47, Joel Fernandes wrote:
> Just rebased on Linus's master and made adjustments. These patches have been

I failed to apply these to both linus and tip master. What's your
baseline commit?

Thanks,
Juri