Resguardo inicial

linux-7.2.3/tools/testing/selftests/sched_ext/.gitignore

@@ -0,0 +1,6 @@
+*
+!*.c
+!*.h
+!Makefile
+!.gitignore
+!config

linux-7.2.3/tools/testing/selftests/sched_ext/Makefile

@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+include ../../../build/Build.include
+include ../../../scripts/Makefile.arch
+include ../../../scripts/Makefile.include
+
+TEST_GEN_PROGS := runner
+
+# override lib.mk's default rules
+OVERRIDE_TARGETS := 1
+include ../lib.mk
+
+CURDIR := $(abspath .)
+REPOROOT := $(abspath ../../../..)
+TOOLSDIR := $(REPOROOT)/tools
+LIBDIR := $(TOOLSDIR)/lib
+BPFDIR := $(LIBDIR)/bpf
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
+GENDIR := $(REPOROOT)/include/generated
+GENHDR := $(GENDIR)/autoconf.h
+SCXTOOLSDIR := $(TOOLSDIR)/sched_ext
+SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include
+
+OUTPUT_DIR := $(OUTPUT)/build
+OBJ_DIR := $(OUTPUT_DIR)/obj
+INCLUDE_DIR := $(OUTPUT_DIR)/include
+BPFOBJ_DIR := $(OBJ_DIR)/libbpf
+SCXOBJ_DIR := $(OBJ_DIR)/sched_ext
+BPFOBJ := $(BPFOBJ_DIR)/libbpf.a
+LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a
+
+DEFAULT_BPFTOOL := $(OUTPUT_DIR)/host/sbin/bpftool
+HOST_OBJ_DIR := $(OBJ_DIR)/host/bpftool
+HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/host/libbpf/
+HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/host/
+HOST_DESTDIR := $(OUTPUT_DIR)/host/
+
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)					\
+		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)		\
+		     ../../../../vmlinux					\
+		     /sys/kernel/btf/vmlinux					\
+		     /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
+
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+
+ifneq ($(wildcard $(GENHDR)),)
+  GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -g -O2 -rdynamic -pthread -Wall -Werror $(GENFLAGS)			\
+	  -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)				\
+	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(CURDIR)/include -I$(SCXTOOLSINCDIR)
+
+# Silence some warnings when compiled with clang
+ifneq ($(LLVM),)
+CFLAGS += -Wno-unused-command-line-argument
+endif
+
+LDFLAGS = -lelf -lz -lpthread -lzstd
+
+IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null |				\
+			grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
+
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) $(2) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+ifneq ($(CROSS_COMPILE),)
+CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif
+
+CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
+
+BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH)					\
+	     $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)		\
+	     -I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat			\
+	     -I$(INCLUDE_DIR) -I$(APIDIR) -I$(SCXTOOLSINCDIR)			\
+	     -I$(REPOROOT)/include						\
+	     $(CLANG_SYS_INCLUDES) 						\
+	     -Wall -Wno-compare-distinct-pointer-types				\
+	     -Wno-incompatible-function-pointer-types				\
+	     -Wno-microsoft-anon-tag						\
+	     -fms-extensions							\
+	     -O2 -mcpu=v3
+
+# sort removes libbpf duplicates when not cross-building
+MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(OBJ_DIR)/libbpf				\
+	       $(OBJ_DIR)/bpftool $(OBJ_DIR)/resolve_btfids			\
+	       $(HOST_OBJ_DIR) $(INCLUDE_DIR) $(SCXOBJ_DIR))
+
+$(MAKE_DIRS):
+	$(call msg,MKDIR,,$@)
+	$(Q)mkdir -p $@
+
+$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)			\
+	   $(APIDIR)/linux/bpf.h						\
+	   | $(OBJ_DIR)/libbpf
+	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(OBJ_DIR)/libbpf/	\
+		    ARCH=$(ARCH) CC="$(CC)" CROSS_COMPILE=$(CROSS_COMPILE)	\
+		    EXTRA_CFLAGS='-g -O0 -fPIC'					\
+		    DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
+
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
+		    $(LIBBPF_OUTPUT) | $(HOST_OBJ_DIR)
+	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
+		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD)		\
+		    EXTRA_CFLAGS='-g -O0'					\
+		    OUTPUT=$(HOST_OBJ_DIR)/					\
+		    LIBBPF_OUTPUT=$(HOST_LIBBPF_OUTPUT)				\
+		    LIBBPF_DESTDIR=$(HOST_LIBBPF_DESTDIR)			\
+		    prefix= DESTDIR=$(HOST_DESTDIR) install-bin
+
+$(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
+ifeq ($(VMLINUX_H),)
+	$(call msg,GEN,,$@)
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(call msg,CP,,$@)
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+$(SCXOBJ_DIR)/%.bpf.o: %.bpf.c $(INCLUDE_DIR)/vmlinux.h	| $(BPFOBJ) $(SCXOBJ_DIR)
+	$(call msg,CLNG-BPF,,$(notdir $@))
+	$(Q)$(CLANG) $(BPF_CFLAGS) -target bpf -c $< -o $@
+
+$(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BPFTOOL) | $(INCLUDE_DIR)
+	$(eval sched=$(notdir $@))
+	$(call msg,GEN-SKEL,,$(sched))
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked1.o) $<
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked2.o) $(<:.o=.linked1.o)
+	$(Q)$(BPFTOOL) gen object $(<:.o=.linked3.o) $(<:.o=.linked2.o)
+	$(Q)diff $(<:.o=.linked2.o) $(<:.o=.linked3.o)
+	$(Q)$(BPFTOOL) gen skeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $@
+	$(Q)$(BPFTOOL) gen subskeleton $(<:.o=.linked3.o) name $(subst .bpf.skel.h,,$(sched)) > $(@:.skel.h=.subskel.h)
+
+################
+# C schedulers #
+################
+
+override define CLEAN
+	rm -rf $(OUTPUT_DIR)
+	rm -f $(TEST_GEN_PROGS)
+endef
+
+# Every testcase takes all of the BPF progs are dependencies by default. This
+# allows testcases to load any BPF scheduler, which is useful for testcases
+# that don't need their own prog to run their test.
+all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubst %.c,%.skel.h,$(prog)))
+
+auto-test-targets :=			\
+	create_dsq			\
+	dequeue				\
+	enq_last_no_enq_fails		\
+	ddsp_bogus_dsq_fail		\
+	ddsp_vtimelocal_fail		\
+	dsp_local_on			\
+	enq_select_cpu			\
+	exit				\
+	hotplug				\
+	init_enable_count		\
+	maximal				\
+	maybe_null			\
+	minimal				\
+	non_scx_kfunc_deny		\
+	nohz_tick			\
+	numa				\
+	allowed_cpus			\
+	peek_dsq			\
+	prog_run			\
+	reload_loop			\
+	select_cpu_dfl			\
+	select_cpu_dfl_nodispatch	\
+	select_cpu_dispatch		\
+	select_cpu_dispatch_bad_dsq	\
+	select_cpu_dispatch_dbl_dsp	\
+	select_cpu_vtime		\
+	rt_stall			\
+	test_example			\
+	total_bw			\
+	cyclic_kick_wait		\
+
+testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
+
+$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ)
+	$(CC) $(CFLAGS) -c $< -o $@
+
+# Create all of the test targets object files, whose testcase objects will be
+# registered into the runner in ELF constructors.
+#
+# Note that we must do double expansion here in order to support conditionally
+# compiling BPF object files only if one is present, as the wildcard Make
+# function doesn't support using implicit rules otherwise.
+$(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR)
+	$(eval test=$(patsubst %.o,%.c,$(notdir $@)))
+	$(CC) $(CFLAGS) -c $< -o $@
+
+$(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR)
+	$(CC) $(CFLAGS) -c $< -o $@
+
+$(OUTPUT)/runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets)
+	@echo "$(testcase-targets)"
+	$(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+
+.DEFAULT_GOAL := all
+
+.DELETE_ON_ERROR:
+
+.SECONDARY:

linux-7.2.3/tools/testing/selftests/sched_ext/allowed_cpus.bpf.c

@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that validates the behavior of scx_bpf_select_cpu_and() by
+ * selecting idle CPUs strictly within a subset of allowed CPUs.
+ *
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+private(PREF_CPUS) struct bpf_cpumask __kptr * allowed_cpumask;
+
+static void
+validate_idle_cpu(const struct task_struct *p, const struct cpumask *allowed, s32 cpu)
+{
+	if (scx_bpf_test_and_clear_cpu_idle(cpu))
+		scx_bpf_error("CPU %d should be marked as busy", cpu);
+
+	if (bpf_cpumask_subset(allowed, p->cpus_ptr) &&
+	    !bpf_cpumask_test_cpu(cpu, allowed))
+		scx_bpf_error("CPU %d not in the allowed domain for %d (%s)",
+			      cpu, p->pid, p->comm);
+}
+
+s32 BPF_STRUCT_OPS(allowed_cpus_select_cpu,
+		   struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	const struct cpumask *allowed;
+	s32 cpu;
+
+	allowed = cast_mask(allowed_cpumask);
+	if (!allowed) {
+		scx_bpf_error("allowed domain not initialized");
+		return -EINVAL;
+	}
+
+	/*
+	 * Select an idle CPU strictly within the allowed domain.
+	 */
+	cpu = scx_bpf_select_cpu_and(p, prev_cpu, wake_flags, allowed, 0);
+	if (cpu >= 0) {
+		validate_idle_cpu(p, allowed, cpu);
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+
+		return cpu;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(allowed_cpus_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	const struct cpumask *allowed;
+	s32 prev_cpu = scx_bpf_task_cpu(p), cpu;
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+
+	allowed = cast_mask(allowed_cpumask);
+	if (!allowed) {
+		scx_bpf_error("allowed domain not initialized");
+		return;
+	}
+
+	/*
+	 * Use scx_bpf_select_cpu_and() to proactively kick an idle CPU
+	 * within @allowed_cpumask, usable by @p.
+	 */
+	cpu = scx_bpf_select_cpu_and(p, prev_cpu, 0, allowed, 0);
+	if (cpu >= 0) {
+		validate_idle_cpu(p, allowed, cpu);
+		scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+	}
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(allowed_cpus_init)
+{
+	struct bpf_cpumask *mask;
+
+	mask = bpf_cpumask_create();
+	if (!mask)
+		return -ENOMEM;
+
+	mask = bpf_kptr_xchg(&allowed_cpumask, mask);
+	if (mask)
+		bpf_cpumask_release(mask);
+
+	bpf_rcu_read_lock();
+
+	/*
+	 * Assign the first online CPU to the allowed domain.
+	 */
+	mask = allowed_cpumask;
+	if (mask) {
+		const struct cpumask *online = scx_bpf_get_online_cpumask();
+
+		bpf_cpumask_set_cpu(bpf_cpumask_first(online), mask);
+		scx_bpf_put_cpumask(online);
+	}
+
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(allowed_cpus_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+struct task_cpu_arg {
+	pid_t pid;
+};
+
+SEC("syscall")
+int select_cpu_from_user(struct task_cpu_arg *input)
+{
+	struct task_struct *p;
+	int cpu;
+
+	p = bpf_task_from_pid(input->pid);
+	if (!p)
+		return -EINVAL;
+
+	bpf_rcu_read_lock();
+	cpu = scx_bpf_select_cpu_and(p, bpf_get_smp_processor_id(), 0, p->cpus_ptr, 0);
+	bpf_rcu_read_unlock();
+
+	bpf_task_release(p);
+
+	return cpu;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops allowed_cpus_ops = {
+	.select_cpu		= (void *)allowed_cpus_select_cpu,
+	.enqueue		= (void *)allowed_cpus_enqueue,
+	.init			= (void *)allowed_cpus_init,
+	.exit			= (void *)allowed_cpus_exit,
+	.name			= "allowed_cpus",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/allowed_cpus.c

@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "allowed_cpus.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct allowed_cpus *skel;
+
+	skel = allowed_cpus__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(allowed_cpus__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static int test_select_cpu_from_user(const struct allowed_cpus *skel)
+{
+	int fd, ret;
+	__u64 args[1];
+
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+
+	args[0] = getpid();
+	fd = bpf_program__fd(skel->progs.select_cpu_from_user);
+	if (fd < 0)
+		return fd;
+
+	ret = bpf_prog_test_run_opts(fd, &attr);
+	if (ret < 0)
+		return ret;
+
+	fprintf(stderr, "%s: CPU %d\n", __func__, attr.retval);
+
+	return 0;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct allowed_cpus *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.allowed_cpus_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	/* Pick an idle CPU from user-space */
+	SCX_FAIL_IF(test_select_cpu_from_user(skel), "Failed to pick idle CPU");
+
+	/* Just sleeping is fine, plenty of scheduling events happening */
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct allowed_cpus *skel = ctx;
+
+	allowed_cpus__destroy(skel);
+}
+
+struct scx_test allowed_cpus = {
+	.name = "allowed_cpus",
+	.description = "Verify scx_bpf_select_cpu_and()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&allowed_cpus)

linux-7.2.3/tools/testing/selftests/sched_ext/config

@@ -0,0 +1,8 @@
+CONFIG_SCHED_CLASS_EXT=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_EXT_GROUP_SCHED=y
+CONFIG_BPF=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y

linux-7.2.3/tools/testing/selftests/sched_ext/create_dsq.bpf.c

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Create and destroy DSQs in a loop.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+void BPF_STRUCT_OPS(create_dsq_exit_task, struct task_struct *p,
+		    struct scx_exit_task_args *args)
+{
+	scx_bpf_destroy_dsq(p->pid);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init_task, struct task_struct *p,
+			     struct scx_init_task_args *args)
+{
+	s32 err;
+
+	err = scx_bpf_create_dsq(p->pid, -1);
+	if (err)
+		scx_bpf_error("Failed to create DSQ for %s[%d]",
+			      p->comm, p->pid);
+
+	return err;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init)
+{
+	u32 i;
+	s32 err;
+
+	bpf_for(i, 0, 1024) {
+		err = scx_bpf_create_dsq(i, -1);
+		if (err) {
+			scx_bpf_error("Failed to create DSQ %d", i);
+			return 0;
+		}
+	}
+
+	bpf_for(i, 0, 1024) {
+		scx_bpf_destroy_dsq(i);
+	}
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops create_dsq_ops = {
+	.init_task		= (void *) create_dsq_init_task,
+	.exit_task		= (void *) create_dsq_exit_task,
+	.init			= (void *) create_dsq_init,
+	.name			= "create_dsq",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/create_dsq.c

@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "create_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct create_dsq *skel;
+
+	skel = create_dsq__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct create_dsq *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.create_dsq_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct create_dsq *skel = ctx;
+
+	create_dsq__destroy(skel);
+}
+
+struct scx_test create_dsq = {
+	.name = "create_dsq",
+	.description = "Create and destroy a dsq in a loop",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&create_dsq)

linux-7.2.3/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c

@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock.
+ *
+ * Three CPUs are designated from userspace. Every enqueue from one of the
+ * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a
+ * persistent A -> B -> C -> A wait cycle pressure.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu_a;
+const volatile s32 test_cpu_b;
+const volatile s32 test_cpu_c;
+
+u64 nr_enqueues;
+u64 nr_wait_kicks;
+
+UEI_DEFINE(uei);
+
+static s32 target_cpu(s32 cpu)
+{
+	if (cpu == test_cpu_a)
+		return test_cpu_b;
+	if (cpu == test_cpu_b)
+		return test_cpu_c;
+	if (cpu == test_cpu_c)
+		return test_cpu_a;
+	return -1;
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 tgt;
+
+	__sync_fetch_and_add(&nr_enqueues, 1);
+
+	if (p->flags & PF_KTHREAD) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				   enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+
+	tgt = target_cpu(this_cpu);
+	if (tgt < 0 || tgt == this_cpu)
+		return;
+
+	__sync_fetch_and_add(&nr_wait_kicks, 1);
+	scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT);
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops cyclic_kick_wait_ops = {
+	.enqueue		= cyclic_kick_wait_enqueue,
+	.exit			= cyclic_kick_wait_exit,
+	.name			= "cyclic_kick_wait",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/cyclic_kick_wait.c

@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Test SCX_KICK_WAIT forward progress under cyclic wait pressure.
+ *
+ * SCX_KICK_WAIT busy-waits until the target CPU enters the scheduling path.
+ * If multiple CPUs form a wait cycle (A waits for B, B waits for C, C waits
+ * for A), all CPUs deadlock unless the implementation breaks the cycle.
+ *
+ * This test creates that scenario: three CPUs are arranged in a ring. The BPF
+ * scheduler's ops.enqueue() kicks the next CPU in the ring with SCX_KICK_WAIT
+ * on every enqueue. Userspace pins 4 worker threads per CPU that loop calling
+ * sched_yield(), generating a steady stream of enqueues and thus sustained
+ * A->B->C->A kick_wait cycle pressure. The test passes if the system remains
+ * responsive for 5 seconds without the scheduler being killed by the watchdog.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <pthread.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <stdint.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "scx_test.h"
+#include "cyclic_kick_wait.bpf.skel.h"
+
+#define WORKERS_PER_CPU	4
+#define NR_TEST_CPUS	3
+#define NR_WORKERS	(NR_TEST_CPUS * WORKERS_PER_CPU)
+
+struct worker_ctx {
+	pthread_t tid;
+	int cpu;
+	volatile bool stop;
+	volatile __u64 iters;
+	bool started;
+};
+
+static void *worker_fn(void *arg)
+{
+	struct worker_ctx *worker = arg;
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(worker->cpu, &mask);
+
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		return (void *)(uintptr_t)errno;
+
+	while (!worker->stop) {
+		sched_yield();
+		worker->iters++;
+	}
+
+	return NULL;
+}
+
+static int join_worker(struct worker_ctx *worker)
+{
+	void *ret;
+	struct timespec ts;
+	int err;
+
+	if (!worker->started)
+		return 0;
+
+	if (clock_gettime(CLOCK_REALTIME, &ts))
+		return -errno;
+
+	ts.tv_sec += 2;
+	err = pthread_timedjoin_np(worker->tid, &ret, &ts);
+	if (err == ETIMEDOUT)
+		pthread_detach(worker->tid);
+	if (err)
+		return -err;
+
+	if ((uintptr_t)ret)
+		return -(int)(uintptr_t)ret;
+
+	return 0;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct cyclic_kick_wait *skel;
+
+	skel = cyclic_kick_wait__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+
+	*ctx = skel;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+	struct worker_ctx workers[NR_WORKERS] = {};
+	struct bpf_link *link = NULL;
+	enum scx_test_status status = SCX_TEST_PASS;
+	int test_cpus[NR_TEST_CPUS];
+	int nr_cpus = 0;
+	cpu_set_t mask;
+	int ret, i;
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		SCX_ERR("Failed to get affinity (%d)", errno);
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < CPU_SETSIZE; i++) {
+		if (CPU_ISSET(i, &mask))
+			test_cpus[nr_cpus++] = i;
+		if (nr_cpus == NR_TEST_CPUS)
+			break;
+	}
+
+	if (nr_cpus < NR_TEST_CPUS)
+		return SCX_TEST_SKIP;
+
+	skel->rodata->test_cpu_a = test_cpus[0];
+	skel->rodata->test_cpu_b = test_cpus[1];
+	skel->rodata->test_cpu_c = test_cpus[2];
+
+	if (cyclic_kick_wait__load(skel)) {
+		SCX_ERR("Failed to load skel");
+		return SCX_TEST_FAIL;
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.cyclic_kick_wait_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].cpu = test_cpus[i / WORKERS_PER_CPU];
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = pthread_create(&workers[i].tid, NULL, worker_fn, &workers[i]);
+		if (ret) {
+			SCX_ERR("Failed to create worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+			goto out;
+		}
+		workers[i].started = true;
+	}
+
+	sleep(5);
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		status = SCX_TEST_FAIL;
+	}
+
+out:
+	for (i = 0; i < NR_WORKERS; i++)
+		workers[i].stop = true;
+
+	for (i = 0; i < NR_WORKERS; i++) {
+		ret = join_worker(&workers[i]);
+		if (ret && status == SCX_TEST_PASS) {
+			SCX_ERR("Failed to join worker thread %d (%d)", i, ret);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	if (link)
+		bpf_link__destroy(link);
+
+	return status;
+}
+
+static void cleanup(void *ctx)
+{
+	struct cyclic_kick_wait *skel = ctx;
+
+	cyclic_kick_wait__destroy(skel);
+}
+
+struct scx_test cyclic_kick_wait = {
+	.name = "cyclic_kick_wait",
+	.description = "Verify SCX_KICK_WAIT forward progress under a 3-CPU wait cycle",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&cyclic_kick_wait)

linux-7.2.3/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+
+	if (cpu >= 0) {
+		/*
+		 * If we dispatch to a bogus DSQ that will fall back to the
+		 * builtin global DSQ, we fail gracefully.
+		 */
+		scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+				       p->scx.dsq_vtime, 0);
+		return cpu;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops ddsp_bogus_dsq_fail_ops = {
+	.select_cpu		= (void *) ddsp_bogus_dsq_fail_select_cpu,
+	.exit			= (void *) ddsp_bogus_dsq_fail_exit,
+	.name			= "ddsp_bogus_dsq_fail",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c

@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "ddsp_bogus_dsq_fail.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel;
+
+	skel = ddsp_bogus_dsq_fail__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ddsp_bogus_dsq_fail_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct ddsp_bogus_dsq_fail *skel = ctx;
+
+	ddsp_bogus_dsq_fail__destroy(skel);
+}
+
+struct scx_test ddsp_bogus_dsq_fail = {
+	.name = "ddsp_bogus_dsq_fail",
+	.description = "Verify we gracefully fail, and fall back to using a "
+		       "built-in DSQ, if we do a direct dispatch to an invalid"
+		       " DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&ddsp_bogus_dsq_fail)

linux-7.2.3/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+
+	if (cpu >= 0) {
+		/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
+		scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+					 p->scx.dsq_vtime, 0);
+		return cpu;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops ddsp_vtimelocal_fail_ops = {
+	.select_cpu		= (void *) ddsp_vtimelocal_fail_select_cpu,
+	.exit			= (void *) ddsp_vtimelocal_fail_exit,
+	.name			= "ddsp_vtimelocal_fail",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c

@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include "ddsp_vtimelocal_fail.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct ddsp_vtimelocal_fail *skel;
+
+	skel = ddsp_vtimelocal_fail__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct ddsp_vtimelocal_fail *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ddsp_vtimelocal_fail_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct ddsp_vtimelocal_fail *skel = ctx;
+
+	ddsp_vtimelocal_fail__destroy(skel);
+}
+
+struct scx_test ddsp_vtimelocal_fail = {
+	.name = "ddsp_vtimelocal_fail",
+	.description = "Verify we gracefully fail, and fall back to using a "
+		       "built-in DSQ, if we do a direct vtime dispatch to a "
+		       "built-in DSQ from DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&ddsp_vtimelocal_fail)

linux-7.2.3/tools/testing/selftests/sched_ext/dequeue.bpf.c

@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that validates ops.dequeue() is called correctly:
+ * - Tasks dispatched to terminal DSQs (local, global) bypass the BPF
+ *   scheduler entirely: no ops.dequeue() should be called
+ * - Tasks dispatched to user DSQs from ops.enqueue() enter BPF custody:
+ *   ops.dequeue() must be called when they leave custody
+ * - Every ops.enqueue() dispatch to non-terminal DSQs is followed by
+ *   exactly one ops.dequeue() (validate 1:1 pairing and state machine)
+ *
+ * Copyright (c) 2026 NVIDIA Corporation.
+ */
+
+#include <scx/common.bpf.h>
+
+#define SHARED_DSQ	0
+
+/*
+ * BPF internal queue.
+ *
+ * Tasks are stored here and consumed from ops.dispatch(), validating that
+ * tasks on BPF internal structures still get ops.dequeue() when they
+ * leave.
+ */
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 32768);
+	__type(value, s32);
+} global_queue SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+/*
+ * Counters to track the lifecycle of tasks:
+ * - enqueue_cnt: Number of times ops.enqueue() was called
+ * - dequeue_cnt: Number of times ops.dequeue() was called (any type)
+ * - dispatch_dequeue_cnt: Number of regular dispatch dequeues (no flag)
+ * - change_dequeue_cnt: Number of property change dequeues
+ * - bpf_queue_full: Number of times the BPF internal queue was full
+ */
+u64 enqueue_cnt, dequeue_cnt, dispatch_dequeue_cnt, change_dequeue_cnt, bpf_queue_full;
+
+/*
+ * Test scenarios:
+ * 0) Dispatch to local DSQ from ops.select_cpu() (terminal DSQ, bypasses BPF
+ *    scheduler, no dequeue callbacks)
+ * 1) Dispatch to global DSQ from ops.select_cpu() (terminal DSQ, bypasses BPF
+ *    scheduler, no dequeue callbacks)
+ * 2) Dispatch to shared user DSQ from ops.select_cpu() (enters BPF scheduler,
+ *    dequeue callbacks expected)
+ * 3) Dispatch to local DSQ from ops.enqueue() (terminal DSQ, bypasses BPF
+ *    scheduler, no dequeue callbacks)
+ * 4) Dispatch to global DSQ from ops.enqueue() (terminal DSQ, bypasses BPF
+ *    scheduler, no dequeue callbacks)
+ * 5) Dispatch to shared user DSQ from ops.enqueue() (enters BPF scheduler,
+ *    dequeue callbacks expected)
+ * 6) BPF internal queue from ops.enqueue(): store task PIDs in ops.enqueue(),
+ *    consume in ops.dispatch() and dispatch to local DSQ (validates dequeue
+ *    for tasks stored in internal BPF data structures)
+ */
+u32 test_scenario;
+
+/*
+ * Per-task state to track lifecycle and validate workflow semantics.
+ * State transitions:
+ *   NONE -> ENQUEUED (on enqueue)
+ *   NONE -> DISPATCHED (on direct dispatch to terminal DSQ)
+ *   ENQUEUED -> DISPATCHED (on dispatch dequeue)
+ *   DISPATCHED -> NONE (on property change dequeue or re-enqueue)
+ *   ENQUEUED -> NONE (on property change dequeue before dispatch)
+ */
+enum task_state {
+	TASK_NONE = 0,
+	TASK_ENQUEUED,
+	TASK_DISPATCHED,
+};
+
+struct task_ctx {
+	enum task_state state; /* Current state in the workflow */
+	u64 enqueue_seq;       /* Sequence number for debugging */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct task_ctx);
+} task_ctx_stor SEC(".maps");
+
+static struct task_ctx *try_lookup_task_ctx(struct task_struct *p)
+{
+	return bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+}
+
+s32 BPF_STRUCT_OPS(dequeue_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	struct task_ctx *tctx;
+
+	tctx = try_lookup_task_ctx(p);
+	if (!tctx)
+		return prev_cpu;
+
+	switch (test_scenario) {
+	case 0:
+		/*
+		 * Direct dispatch to the local DSQ.
+		 *
+		 * Task bypasses BPF scheduler entirely: no enqueue
+		 * tracking, no ops.dequeue() callbacks.
+		 */
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+		tctx->state = TASK_DISPATCHED;
+		break;
+	case 1:
+		/*
+		 * Direct dispatch to the global DSQ.
+		 *
+		 * Task bypasses BPF scheduler entirely: no enqueue
+		 * tracking, no ops.dequeue() callbacks.
+		 */
+		scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+		tctx->state = TASK_DISPATCHED;
+		break;
+	case 2:
+		/*
+		 * Dispatch to a shared user DSQ.
+		 *
+		 * Task enters BPF scheduler management: track
+		 * enqueue/dequeue lifecycle and validate state
+		 * transitions.
+		 */
+		if (tctx->state == TASK_ENQUEUED)
+			scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu",
+				      p->pid, p->comm, tctx->enqueue_seq);
+
+		scx_bpf_dsq_insert(p, SHARED_DSQ, SCX_SLICE_DFL, 0);
+
+		__sync_fetch_and_add(&enqueue_cnt, 1);
+
+		tctx->state = TASK_ENQUEUED;
+		tctx->enqueue_seq++;
+		break;
+	}
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(dequeue_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	struct task_ctx *tctx;
+	s32 pid = p->pid;
+
+	tctx = try_lookup_task_ctx(p);
+	if (!tctx)
+		return;
+
+	switch (test_scenario) {
+	case 3:
+		/*
+		 * Direct dispatch to the local DSQ.
+		 *
+		 * Task bypasses BPF scheduler entirely: no enqueue
+		 * tracking, no ops.dequeue() callbacks.
+		 */
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, enq_flags);
+		tctx->state = TASK_DISPATCHED;
+		break;
+	case 4:
+		/*
+		 * Direct dispatch to the global DSQ.
+		 *
+		 * Task bypasses BPF scheduler entirely: no enqueue
+		 * tracking, no ops.dequeue() callbacks.
+		 */
+		scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+		tctx->state = TASK_DISPATCHED;
+		break;
+	case 5:
+		/*
+		 * Dispatch to shared user DSQ.
+		 *
+		 * Task enters BPF scheduler management: track
+		 * enqueue/dequeue lifecycle and validate state
+		 * transitions.
+		 */
+		if (tctx->state == TASK_ENQUEUED)
+			scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu",
+				      p->pid, p->comm, tctx->enqueue_seq);
+
+		scx_bpf_dsq_insert(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags);
+
+		__sync_fetch_and_add(&enqueue_cnt, 1);
+
+		tctx->state = TASK_ENQUEUED;
+		tctx->enqueue_seq++;
+		break;
+	case 6:
+		/*
+		 * Store task in BPF internal queue.
+		 *
+		 * Task enters BPF scheduler management: track
+		 * enqueue/dequeue lifecycle and validate state
+		 * transitions.
+		 */
+		if (tctx->state == TASK_ENQUEUED)
+			scx_bpf_error("%d (%s): enqueue while in ENQUEUED state seq=%llu",
+				      p->pid, p->comm, tctx->enqueue_seq);
+
+		if (bpf_map_push_elem(&global_queue, &pid, 0)) {
+			scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+			__sync_fetch_and_add(&bpf_queue_full, 1);
+
+			tctx->state = TASK_DISPATCHED;
+		} else {
+			__sync_fetch_and_add(&enqueue_cnt, 1);
+
+			tctx->state = TASK_ENQUEUED;
+			tctx->enqueue_seq++;
+		}
+		break;
+	default:
+		/* For all other scenarios, dispatch to the global DSQ */
+		scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+		tctx->state = TASK_DISPATCHED;
+		break;
+	}
+
+	scx_bpf_kick_cpu(scx_bpf_task_cpu(p), SCX_KICK_IDLE);
+}
+
+void BPF_STRUCT_OPS(dequeue_dequeue, struct task_struct *p, u64 deq_flags)
+{
+	struct task_ctx *tctx;
+
+	__sync_fetch_and_add(&dequeue_cnt, 1);
+
+	tctx = try_lookup_task_ctx(p);
+	if (!tctx)
+		return;
+
+	/*
+	 * For scenarios 0, 1, 3, and 4 (terminal DSQs: local and global),
+	 * ops.dequeue() should never be called because tasks bypass the
+	 * BPF scheduler entirely. If we get here, it's a kernel bug.
+	 */
+	if (test_scenario == 0 || test_scenario == 3) {
+		scx_bpf_error("%d (%s): dequeue called for local DSQ scenario",
+			      p->pid, p->comm);
+		return;
+	}
+
+	if (test_scenario == 1 || test_scenario == 4) {
+		scx_bpf_error("%d (%s): dequeue called for global DSQ scenario",
+			      p->pid, p->comm);
+		return;
+	}
+
+	if (deq_flags & SCX_DEQ_SCHED_CHANGE) {
+		/*
+		 * Property change interrupting the workflow. Valid from
+		 * both ENQUEUED and DISPATCHED states. Transitions task
+		 * back to NONE state.
+		 */
+		__sync_fetch_and_add(&change_dequeue_cnt, 1);
+
+		/* Validate state transition */
+		if (tctx->state != TASK_ENQUEUED && tctx->state != TASK_DISPATCHED)
+			scx_bpf_error("%d (%s): invalid property change dequeue state=%d seq=%llu",
+				      p->pid, p->comm, tctx->state, tctx->enqueue_seq);
+
+		/*
+		 * Transition back to NONE: task outside scheduler control.
+		 *
+		 * Scenario 6: dispatch() checks tctx->state after popping a
+		 * PID, if the task is in state NONE, it was dequeued by
+		 * property change and must not be dispatched (this
+		 * prevents "target CPU not allowed").
+		 */
+		tctx->state = TASK_NONE;
+	} else {
+		/*
+		 * Regular dispatch dequeue: kernel is moving the task from
+		 * BPF custody to a terminal DSQ. Normally we come from
+		 * ENQUEUED state. We can also see TASK_NONE if the task
+		 * was dequeued by property change (SCX_DEQ_SCHED_CHANGE)
+		 * while it was already on a DSQ (dispatched but not yet
+		 * consumed); in that case we just leave state as NONE.
+		 */
+		__sync_fetch_and_add(&dispatch_dequeue_cnt, 1);
+
+		/*
+		 * Must be ENQUEUED (normal path) or NONE (already dequeued
+		 * by property change while on a DSQ).
+		 */
+		if (tctx->state != TASK_ENQUEUED && tctx->state != TASK_NONE)
+			scx_bpf_error("%d (%s): dispatch dequeue from state %d seq=%llu",
+				      p->pid, p->comm, tctx->state, tctx->enqueue_seq);
+
+		if (tctx->state == TASK_ENQUEUED)
+			tctx->state = TASK_DISPATCHED;
+
+		/* NONE: leave as-is, task was already property-change dequeued */
+	}
+}
+
+void BPF_STRUCT_OPS(dequeue_dispatch, s32 cpu, struct task_struct *prev)
+{
+	if (test_scenario == 6) {
+		struct task_ctx *tctx;
+		struct task_struct *p;
+		s32 pid;
+
+		if (bpf_map_pop_elem(&global_queue, &pid))
+			return;
+
+		p = bpf_task_from_pid(pid);
+		if (!p)
+			return;
+
+		/*
+		 * If the task was dequeued by property change
+		 * (ops.dequeue() set tctx->state = TASK_NONE), skip
+		 * dispatch.
+		 */
+		tctx = try_lookup_task_ctx(p);
+		if (!tctx || tctx->state == TASK_NONE) {
+			bpf_task_release(p);
+			return;
+		}
+
+		/*
+		 * Dispatch to this CPU's local DSQ if allowed, otherwise
+		 * fallback to the global DSQ.
+		 */
+		if (bpf_cpumask_test_cpu(cpu, p->cpus_ptr))
+			scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_DFL, 0);
+		else
+			scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+
+		bpf_task_release(p);
+	} else {
+		scx_bpf_dsq_move_to_local(SHARED_DSQ, 0);
+	}
+}
+
+s32 BPF_STRUCT_OPS(dequeue_init_task, struct task_struct *p,
+		   struct scx_init_task_args *args)
+{
+	struct task_ctx *tctx;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!tctx)
+		return -ENOMEM;
+
+	return 0;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(dequeue_init)
+{
+	s32 ret;
+
+	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(dequeue_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops dequeue_ops = {
+	.select_cpu		= (void *)dequeue_select_cpu,
+	.enqueue		= (void *)dequeue_enqueue,
+	.dequeue		= (void *)dequeue_dequeue,
+	.dispatch		= (void *)dequeue_dispatch,
+	.init_task		= (void *)dequeue_init_task,
+	.init			= (void *)dequeue_init,
+	.exit			= (void *)dequeue_exit,
+	.flags			= SCX_OPS_ENQ_LAST,
+	.name			= "dequeue_test",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/dequeue.c

@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 NVIDIA Corporation.
+ */
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <unistd.h>
+#include <signal.h>
+#include <time.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <sched.h>
+#include <pthread.h>
+#include "scx_test.h"
+#include "dequeue.bpf.skel.h"
+
+#define NUM_WORKERS 8
+#define AFFINITY_HAMMER_MS 500
+
+/*
+ * Worker function that creates enqueue/dequeue events via CPU work and
+ * sleep.
+ */
+static void worker_fn(int id)
+{
+	int i;
+	volatile int sum = 0;
+
+	for (i = 0; i < 1000; i++) {
+		volatile int j;
+
+		/* Do some work to trigger scheduling events */
+		for (j = 0; j < 10000; j++)
+			sum += j;
+		asm volatile("" : : "r"(sum));
+
+		/* Sleep to trigger dequeue */
+		usleep(1000 + (id * 100));
+	}
+
+	exit(0);
+}
+
+/*
+ * This thread changes workers' affinity from outside so that some changes
+ * hit tasks while they are still in the scheduler's queue and trigger
+ * property-change dequeues.
+ */
+static void *affinity_hammer_fn(void *arg)
+{
+	pid_t *pids = arg;
+	cpu_set_t cpuset;
+	int i = 0, n = NUM_WORKERS;
+	struct timespec start, now;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	while (1) {
+		int w = i % n;
+		int cpu = (i / n) % 4;
+
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu, &cpuset);
+		sched_setaffinity(pids[w], sizeof(cpuset), &cpuset);
+		i++;
+
+		/* Check elapsed time every 256 iterations to limit gettime cost */
+		if ((i & 255) == 0) {
+			long long elapsed_ms;
+
+			clock_gettime(CLOCK_MONOTONIC, &now);
+			elapsed_ms = (now.tv_sec - start.tv_sec) * 1000LL +
+				     (now.tv_nsec - start.tv_nsec) / 1000000;
+			if (elapsed_ms >= AFFINITY_HAMMER_MS)
+				break;
+		}
+	}
+	return NULL;
+}
+
+static enum scx_test_status run_scenario(struct dequeue *skel, u32 scenario,
+					 const char *scenario_name)
+{
+	struct bpf_link *link;
+	pid_t pids[NUM_WORKERS];
+	pthread_t hammer;
+
+	int i, status;
+	u64 enq_start, deq_start,
+	    dispatch_deq_start, change_deq_start, bpf_queue_full_start;
+	u64 enq_delta, deq_delta,
+	    dispatch_deq_delta, change_deq_delta, bpf_queue_full_delta;
+
+	/* Set the test scenario */
+	skel->bss->test_scenario = scenario;
+
+	/* Record starting counts */
+	enq_start = skel->bss->enqueue_cnt;
+	deq_start = skel->bss->dequeue_cnt;
+	dispatch_deq_start = skel->bss->dispatch_dequeue_cnt;
+	change_deq_start = skel->bss->change_dequeue_cnt;
+	bpf_queue_full_start = skel->bss->bpf_queue_full;
+
+	link = bpf_map__attach_struct_ops(skel->maps.dequeue_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops for scenario %s", scenario_name);
+
+	/* Fork worker processes to generate enqueue/dequeue events */
+	for (i = 0; i < NUM_WORKERS; i++) {
+		pids[i] = fork();
+		SCX_FAIL_IF(pids[i] < 0, "Failed to fork worker %d", i);
+
+		if (pids[i] == 0) {
+			worker_fn(i);
+			/* Should not reach here */
+			exit(1);
+		}
+	}
+
+	/*
+	 * Run an "affinity hammer" so that some property changes hit tasks
+	 * while they are still in BPF custody (e.g., in user DSQ or BPF
+	 * queue), triggering SCX_DEQ_SCHED_CHANGE dequeues.
+	 */
+	SCX_FAIL_IF(pthread_create(&hammer, NULL, affinity_hammer_fn, pids) != 0,
+		    "Failed to create affinity hammer thread");
+	pthread_join(hammer, NULL);
+
+	/* Wait for all workers to complete */
+	for (i = 0; i < NUM_WORKERS; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for worker %d", i);
+		SCX_FAIL_IF(status != 0, "Worker %d exited with status %d", i, status);
+	}
+
+	bpf_link__destroy(link);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG));
+
+	/* Calculate deltas */
+	enq_delta = skel->bss->enqueue_cnt - enq_start;
+	deq_delta = skel->bss->dequeue_cnt - deq_start;
+	dispatch_deq_delta = skel->bss->dispatch_dequeue_cnt - dispatch_deq_start;
+	change_deq_delta = skel->bss->change_dequeue_cnt - change_deq_start;
+	bpf_queue_full_delta = skel->bss->bpf_queue_full - bpf_queue_full_start;
+
+	printf("%s:\n", scenario_name);
+	printf("  enqueues: %lu\n", (unsigned long)enq_delta);
+	printf("  dequeues: %lu (dispatch: %lu, property_change: %lu)\n",
+	       (unsigned long)deq_delta,
+	       (unsigned long)dispatch_deq_delta,
+	       (unsigned long)change_deq_delta);
+	printf("  BPF queue full: %lu\n", (unsigned long)bpf_queue_full_delta);
+
+	/*
+	 * Validate enqueue/dequeue lifecycle tracking.
+	 *
+	 * For scenarios 0, 1, 3, 4 (local and global DSQs from
+	 * ops.select_cpu() and ops.enqueue()), both enqueues and dequeues
+	 * should be 0 because tasks bypass the BPF scheduler entirely:
+	 * tasks never enter BPF scheduler's custody.
+	 *
+	 * For scenarios 2, 5, 6 (user DSQ or BPF internal queue) we expect
+	 * both enqueues and dequeues.
+	 *
+	 * The BPF code does strict state machine validation with
+	 * scx_bpf_error() to ensure the workflow semantics are correct.
+	 *
+	 * If we reach this point without errors, the semantics are
+	 * validated correctly.
+	 */
+	if (scenario == 0 || scenario == 1 ||
+	    scenario == 3 || scenario == 4) {
+		/* Tasks bypass BPF scheduler completely */
+		SCX_EQ(enq_delta, 0);
+		SCX_EQ(deq_delta, 0);
+		SCX_EQ(dispatch_deq_delta, 0);
+		SCX_EQ(change_deq_delta, 0);
+	} else {
+		/*
+		 * User DSQ from ops.enqueue() or ops.select_cpu(): tasks
+		 * enter BPF scheduler's custody.
+		 *
+		 * Also validate 1:1 enqueue/dequeue pairing.
+		 */
+		SCX_GT(enq_delta, 0);
+		SCX_GT(deq_delta, 0);
+		SCX_EQ(enq_delta, deq_delta);
+	}
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct dequeue *skel;
+
+	skel = dequeue__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(dequeue__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct dequeue *skel = ctx;
+	enum scx_test_status status;
+
+	status = run_scenario(skel, 0, "Scenario 0: Local DSQ from ops.select_cpu()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 1, "Scenario 1: Global DSQ from ops.select_cpu()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 2, "Scenario 2: User DSQ from ops.select_cpu()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 3, "Scenario 3: Local DSQ from ops.enqueue()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 4, "Scenario 4: Global DSQ from ops.enqueue()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 5, "Scenario 5: User DSQ from ops.enqueue()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_scenario(skel, 6, "Scenario 6: BPF queue from ops.enqueue()");
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	printf("\n=== Summary ===\n");
+	printf("Total enqueues: %lu\n", (unsigned long)skel->bss->enqueue_cnt);
+	printf("Total dequeues: %lu\n", (unsigned long)skel->bss->dequeue_cnt);
+	printf("  Dispatch dequeues: %lu (no flag, normal workflow)\n",
+	       (unsigned long)skel->bss->dispatch_dequeue_cnt);
+	printf("  Property change dequeues: %lu (SCX_DEQ_SCHED_CHANGE flag)\n",
+	       (unsigned long)skel->bss->change_dequeue_cnt);
+	printf("  BPF queue full: %lu\n",
+	       (unsigned long)skel->bss->bpf_queue_full);
+	printf("\nAll scenarios passed - no state machine violations detected\n");
+	printf("-> Validated: Local DSQ dispatch bypasses BPF scheduler\n");
+	printf("-> Validated: Global DSQ dispatch bypasses BPF scheduler\n");
+	printf("-> Validated: User DSQ dispatch triggers ops.dequeue() callbacks\n");
+	printf("-> Validated: Dispatch dequeues have no flags (normal workflow)\n");
+	printf("-> Validated: Property change dequeues have SCX_DEQ_SCHED_CHANGE flag\n");
+	printf("-> Validated: No duplicate enqueues or invalid state transitions\n");
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct dequeue *skel = ctx;
+
+	dequeue__destroy(skel);
+}
+
+struct scx_test dequeue_test = {
+	.name = "dequeue",
+	.description = "Verify ops.dequeue() semantics",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+
+REGISTER_SCX_TEST(&dequeue_test)

linux-7.2.3/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c

@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+const volatile s32 nr_cpus;
+
+UEI_DEFINE(uei);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 8192);
+	__type(value, s32);
+} queue SEC(".maps");
+
+s32 BPF_STRUCT_OPS(dsp_local_on_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 pid = p->pid;
+
+	if (bpf_map_push_elem(&queue, &pid, 0))
+		scx_bpf_error("Failed to enqueue %s[%d]", p->comm, p->pid);
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
+{
+	s32 pid, target;
+	struct task_struct *p;
+
+	if (bpf_map_pop_elem(&queue, &pid))
+		return;
+
+	p = bpf_task_from_pid(pid);
+	if (!p)
+		return;
+
+	if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p))
+		target = bpf_get_prandom_u32() % nr_cpus;
+	else
+		target = scx_bpf_task_cpu(p);
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+	bpf_task_release(p);
+}
+
+void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops dsp_local_on_ops = {
+	.select_cpu		= (void *) dsp_local_on_select_cpu,
+	.enqueue		= (void *) dsp_local_on_enqueue,
+	.dispatch		= (void *) dsp_local_on_dispatch,
+	.exit			= (void *) dsp_local_on_exit,
+	.name			= "dsp_local_on",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/dsp_local_on.c

@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include "dsp_local_on.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct dsp_local_on *skel;
+
+	skel = dsp_local_on__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+	SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel");
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct dsp_local_on *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.dsp_local_on_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	/* Just sleeping is fine, plenty of scheduling events happening */
+	sleep(1);
+
+	bpf_link__destroy(link);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG));
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct dsp_local_on *skel = ctx;
+
+	dsp_local_on__destroy(skel);
+}
+
+struct scx_test dsp_local_on = {
+	.name = "dsp_local_on",
+	.description = "Verify we can directly dispatch tasks to a local DSQs "
+		       "from ops.dispatch()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&dsp_local_on)

linux-7.2.3/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u32 exit_kind;
+
+void BPF_STRUCT_OPS_SLEEPABLE(enq_last_no_enq_fails_exit, struct scx_exit_info *info)
+{
+	exit_kind = info->kind;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_last_no_enq_fails_ops = {
+	.name			= "enq_last_no_enq_fails",
+	/* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */
+	.flags			= SCX_OPS_ENQ_LAST,
+	.exit			= (void *) enq_last_no_enq_fails_exit,
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c

@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "enq_last_no_enq_fails.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct enq_last_no_enq_fails *skel;
+
+	skel = enq_last_no_enq_fails__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct enq_last_no_enq_fails *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops);
+	if (!link) {
+		SCX_ERR("Incorrectly failed at attaching scheduler");
+		return SCX_TEST_FAIL;
+	}
+	if (!skel->bss->exit_kind) {
+		SCX_ERR("Incorrectly stayed loaded");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct enq_last_no_enq_fails *skel = ctx;
+
+	enq_last_no_enq_fails__destroy(skel);
+}
+
+struct scx_test enq_last_no_enq_fails = {
+	.name = "enq_last_no_enq_fails",
+	.description = "Verify we eject a scheduler if we specify "
+		       "the SCX_OPS_ENQ_LAST flag without defining "
+		       "ops.enqueue()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&enq_last_no_enq_fails)

linux-7.2.3/tools/testing/selftests/sched_ext/enq_select_cpu.bpf.c

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(enq_select_cpu_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/* Bounce all tasks to ops.enqueue() */
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(enq_select_cpu_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 cpu, prev_cpu = scx_bpf_task_cpu(p);
+	bool found = false;
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, 0, &found);
+	if (found) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_DFL, enq_flags);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(enq_select_cpu_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+struct task_cpu_arg {
+	pid_t pid;
+};
+
+SEC("syscall")
+int select_cpu_from_user(struct task_cpu_arg *input)
+{
+	struct task_struct *p;
+	bool found = false;
+	s32 cpu;
+
+	p = bpf_task_from_pid(input->pid);
+	if (!p)
+		return -EINVAL;
+
+	bpf_rcu_read_lock();
+	cpu = scx_bpf_select_cpu_dfl(p, bpf_get_smp_processor_id(), 0, &found);
+	if (!found)
+		cpu = -EBUSY;
+	bpf_rcu_read_unlock();
+
+	bpf_task_release(p);
+
+	return cpu;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_select_cpu_ops = {
+	.select_cpu		= (void *)enq_select_cpu_select_cpu,
+	.enqueue		= (void *)enq_select_cpu_enqueue,
+	.exit			= (void *)enq_select_cpu_exit,
+	.name			= "enq_select_cpu",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/enq_select_cpu.c

@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "enq_select_cpu.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct enq_select_cpu *skel;
+
+	skel = enq_select_cpu__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(enq_select_cpu__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static int test_select_cpu_from_user(const struct enq_select_cpu *skel)
+{
+	int fd, ret;
+	__u64 args[1];
+
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+
+	args[0] = getpid();
+	fd = bpf_program__fd(skel->progs.select_cpu_from_user);
+	if (fd < 0)
+		return fd;
+
+	ret = bpf_prog_test_run_opts(fd, &attr);
+	if (ret < 0)
+		return ret;
+
+	fprintf(stderr, "%s: CPU %d\n", __func__, attr.retval);
+
+	return 0;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct enq_select_cpu *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.enq_select_cpu_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	/* Pick an idle CPU from user-space */
+	SCX_FAIL_IF(test_select_cpu_from_user(skel), "Failed to pick idle CPU");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct enq_select_cpu *skel = ctx;
+
+	enq_select_cpu__destroy(skel);
+}
+
+struct scx_test enq_select_cpu = {
+	.name = "enq_select_cpu",
+	.description = "Verify scx_bpf_select_cpu_dfl() from multiple contexts",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&enq_select_cpu)

linux-7.2.3/tools/testing/selftests/sched_ext/exit.bpf.c

@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+#include "exit_test.h"
+
+const volatile int exit_point;
+UEI_DEFINE(uei);
+
+#define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point)
+
+#define DSQ_ID 0
+
+s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	bool found;
+
+	if (exit_point == EXIT_SELECT_CPU)
+		EXIT_CLEANLY();
+
+	return scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &found);
+}
+
+void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	if (exit_point == EXIT_ENQUEUE)
+		EXIT_CLEANLY();
+
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (exit_point == EXIT_DISPATCH)
+		EXIT_CLEANLY();
+
+	scx_bpf_dsq_move_to_local(DSQ_ID, 0);
+}
+
+void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
+{
+	if (exit_point == EXIT_ENABLE)
+		EXIT_CLEANLY();
+}
+
+s32 BPF_STRUCT_OPS(exit_init_task, struct task_struct *p,
+		    struct scx_init_task_args *args)
+{
+	if (exit_point == EXIT_INIT_TASK)
+		EXIT_CLEANLY();
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(exit_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init)
+{
+	if (exit_point == EXIT_INIT)
+		EXIT_CLEANLY();
+
+	return scx_bpf_create_dsq(DSQ_ID, -1);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops exit_ops = {
+	.select_cpu		= (void *) exit_select_cpu,
+	.enqueue		= (void *) exit_enqueue,
+	.dispatch		= (void *) exit_dispatch,
+	.init_task		= (void *) exit_init_task,
+	.enable			= (void *) exit_enable,
+	.exit			= (void *) exit_exit,
+	.init			= (void *) exit_init,
+	.name			= "exit",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/exit.c

@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "exit.bpf.skel.h"
+#include "scx_test.h"
+
+#include "exit_test.h"
+
+static enum scx_test_status run(void *ctx)
+{
+	enum exit_test_case tc;
+
+	for (tc = 0; tc < NUM_EXITS; tc++) {
+		struct exit *skel;
+		struct bpf_link *link;
+		char buf[16];
+
+		/*
+		 * On single-CPU systems, ops.select_cpu() is never
+		 * invoked, so skip this test to avoid getting stuck
+		 * indefinitely.
+		 */
+		if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1)
+			continue;
+
+		skel = exit__open();
+		SCX_ENUM_INIT(skel);
+		skel->rodata->exit_point = tc;
+		SCX_FAIL_IF(exit__load(skel), "Failed to load skel");
+		link = bpf_map__attach_struct_ops(skel->maps.exit_ops);
+		if (!link) {
+			SCX_ERR("Failed to attach scheduler");
+			exit__destroy(skel);
+			return SCX_TEST_FAIL;
+		}
+
+		/* Assumes uei.kind is written last */
+		while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE))
+			sched_yield();
+
+		SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF));
+		SCX_EQ(skel->data->uei.exit_code, tc);
+		sprintf(buf, "%d", tc);
+		SCX_ASSERT(!strcmp(skel->data->uei.msg, buf));
+		bpf_link__destroy(link);
+		exit__destroy(skel);
+	}
+
+	return SCX_TEST_PASS;
+}
+
+struct scx_test exit_test = {
+	.name = "exit",
+	.description = "Verify we can cleanly exit a scheduler in multiple places",
+	.run = run,
+};
+REGISTER_SCX_TEST(&exit_test)

linux-7.2.3/tools/testing/selftests/sched_ext/exit_test.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __EXIT_TEST_H__
+#define __EXIT_TEST_H__
+
+enum exit_test_case {
+	EXIT_SELECT_CPU,
+	EXIT_ENQUEUE,
+	EXIT_DISPATCH,
+	EXIT_ENABLE,
+	EXIT_INIT_TASK,
+	EXIT_INIT,
+	NUM_EXITS,
+};
+
+#endif  // __EXIT_TEST_H__

linux-7.2.3/tools/testing/selftests/sched_ext/hotplug.bpf.c

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+#include "hotplug_test.h"
+
+UEI_DEFINE(uei);
+
+void BPF_STRUCT_OPS(hotplug_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+static void exit_from_hotplug(s32 cpu, bool onlining)
+{
+	/*
+	 * Ignored, just used to verify that we can invoke blocking kfuncs
+	 * from the hotplug path.
+	 */
+	scx_bpf_create_dsq(0, -1);
+
+	s64 code = SCX_ECODE_ACT_RESTART | HOTPLUG_EXIT_RSN;
+
+	if (onlining)
+		code |= HOTPLUG_ONLINING;
+
+	scx_bpf_exit(code, "hotplug event detected (%d going %s)", cpu,
+		     onlining ? "online" : "offline");
+}
+
+void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_online, s32 cpu)
+{
+	exit_from_hotplug(cpu, true);
+}
+
+void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu)
+{
+	exit_from_hotplug(cpu, false);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops hotplug_cb_ops = {
+	.cpu_online		= (void *) hotplug_cpu_online,
+	.cpu_offline		= (void *) hotplug_cpu_offline,
+	.exit			= (void *) hotplug_exit,
+	.name			= "hotplug_cbs",
+	.timeout_ms		= 1000U,
+};
+
+SEC(".struct_ops.link")
+struct sched_ext_ops hotplug_nocb_ops = {
+	.exit			= (void *) hotplug_exit,
+	.name			= "hotplug_nocbs",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/hotplug.c

@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "hotplug_test.h"
+#include "hotplug.bpf.skel.h"
+#include "scx_test.h"
+#include "util.h"
+
+const char *online_path = "/sys/devices/system/cpu/cpu1/online";
+
+static bool is_cpu_online(void)
+{
+	return file_read_long(online_path) > 0;
+}
+
+static void toggle_online_status(bool online)
+{
+	long val = online ? 1 : 0;
+	int ret;
+
+	ret = file_write_long(online_path, val);
+	if (ret != 0)
+		fprintf(stderr, "Failed to bring CPU %s (%s)",
+			online ? "online" : "offline", strerror(errno));
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	if (!is_cpu_online())
+		return SCX_TEST_SKIP;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined)
+{
+	struct hotplug *skel;
+	struct bpf_link *link;
+	long kind, code;
+
+	SCX_ASSERT(is_cpu_online());
+
+	skel = hotplug__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel");
+
+	/* Testing the offline -> online path, so go offline before starting */
+	if (onlining)
+		toggle_online_status(0);
+
+	if (cbs_defined) {
+		kind = SCX_KIND_VAL(SCX_EXIT_UNREG_BPF);
+		code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | HOTPLUG_EXIT_RSN;
+		if (onlining)
+			code |= HOTPLUG_ONLINING;
+	} else {
+		kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN);
+		code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) |
+		       SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG);
+	}
+
+	if (cbs_defined)
+		link = bpf_map__attach_struct_ops(skel->maps.hotplug_cb_ops);
+	else
+		link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops);
+
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		hotplug__destroy(skel);
+		return SCX_TEST_FAIL;
+	}
+
+	toggle_online_status(onlining ? 1 : 0);
+
+	while (!UEI_EXITED(skel, uei))
+		sched_yield();
+
+	SCX_EQ(skel->data->uei.kind, kind);
+	SCX_EQ(UEI_REPORT(skel, uei), code);
+
+	if (!onlining)
+		toggle_online_status(1);
+
+	bpf_link__destroy(link);
+	hotplug__destroy(skel);
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status test_hotplug_attach(void)
+{
+	struct hotplug *skel;
+	struct bpf_link *link;
+	enum scx_test_status status = SCX_TEST_PASS;
+	long kind, code;
+
+	SCX_ASSERT(is_cpu_online());
+	SCX_ASSERT(scx_hotplug_seq() > 0);
+
+	skel = SCX_OPS_OPEN(hotplug_nocb_ops, hotplug);
+	SCX_ASSERT(skel);
+
+	SCX_OPS_LOAD(skel, hotplug_nocb_ops, hotplug, uei);
+
+	/*
+	 * Take the CPU offline to increment the global hotplug seq, which
+	 * should cause attach to fail due to us setting the hotplug seq above
+	 */
+	toggle_online_status(0);
+	link = bpf_map__attach_struct_ops(skel->maps.hotplug_nocb_ops);
+
+	toggle_online_status(1);
+
+	SCX_ASSERT(link);
+	while (!UEI_EXITED(skel, uei))
+		sched_yield();
+
+	kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN);
+	code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) |
+	       SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG);
+	SCX_EQ(skel->data->uei.kind, kind);
+	SCX_EQ(UEI_REPORT(skel, uei), code);
+
+	bpf_link__destroy(link);
+	hotplug__destroy(skel);
+
+	return status;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+
+#define HP_TEST(__onlining, __cbs_defined) ({				\
+	if (test_hotplug(__onlining, __cbs_defined) != SCX_TEST_PASS)	\
+		return SCX_TEST_FAIL;					\
+})
+
+	HP_TEST(true, true);
+	HP_TEST(false, true);
+	HP_TEST(true, false);
+	HP_TEST(false, false);
+
+#undef HP_TEST
+
+	return test_hotplug_attach();
+}
+
+static void cleanup(void *ctx)
+{
+	toggle_online_status(1);
+}
+
+struct scx_test hotplug_test = {
+	.name = "hotplug",
+	.description = "Verify hotplug behavior",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&hotplug_test)

linux-7.2.3/tools/testing/selftests/sched_ext/hotplug_test.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __HOTPLUG_TEST_H__
+#define __HOTPLUG_TEST_H__
+
+enum hotplug_test_flags {
+	HOTPLUG_EXIT_RSN = 1LLU << 0,
+	HOTPLUG_ONLINING = 1LLU << 1,
+};
+
+#endif  // # __HOTPLUG_TEST_H__

linux-7.2.3/tools/testing/selftests/sched_ext/init_enable_count.bpf.c

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that verifies that we do proper counting of init, enable, etc
+ * callbacks.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 init_task_cnt, exit_task_cnt, enable_cnt, disable_cnt;
+u64 init_fork_cnt, init_transition_cnt;
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(cnt_init_task, struct task_struct *p,
+			     struct scx_init_task_args *args)
+{
+	__sync_fetch_and_add(&init_task_cnt, 1);
+
+	if (args->fork)
+		__sync_fetch_and_add(&init_fork_cnt, 1);
+	else
+		__sync_fetch_and_add(&init_transition_cnt, 1);
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(cnt_exit_task, struct task_struct *p)
+{
+	__sync_fetch_and_add(&exit_task_cnt, 1);
+}
+
+void BPF_STRUCT_OPS(cnt_enable, struct task_struct *p)
+{
+	__sync_fetch_and_add(&enable_cnt, 1);
+}
+
+void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p)
+{
+	__sync_fetch_and_add(&disable_cnt, 1);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops init_enable_count_ops = {
+	.init_task	= (void *) cnt_init_task,
+	.exit_task	= (void *) cnt_exit_task,
+	.enable		= (void *) cnt_enable,
+	.disable	= (void *) cnt_disable,
+	.name		= "init_enable_count",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/init_enable_count.c

@@ -0,0 +1,170 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <signal.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sched.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include "scx_test.h"
+#include "init_enable_count.bpf.skel.h"
+
+#define SCHED_EXT 7
+
+static enum scx_test_status run_test(bool global)
+{
+	struct init_enable_count *skel;
+	struct bpf_link *link;
+	const u32 num_children = 5, num_pre_forks = 1024;
+	int ret, i, status;
+	struct sched_param param = {};
+	pid_t pids[num_pre_forks];
+	int pipe_fds[2];
+
+	SCX_FAIL_IF(pipe(pipe_fds) < 0, "Failed to create pipe");
+
+	skel = init_enable_count__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+
+	if (!global)
+		skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
+
+	SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel");
+
+	/*
+	 * Fork a bunch of children before we attach the scheduler so that we
+	 * ensure (at least in practical terms) that there are more tasks that
+	 * transition from SCHED_OTHER -> SCHED_EXT than there are tasks that
+	 * take the fork() path either below or in other processes.
+	 *
+	 * All children will block on read() on the pipe until the parent closes
+	 * the write end after attaching the scheduler, which signals all of
+	 * them to exit simultaneously. Auto-reap so we don't have to wait on
+	 * them.
+	 */
+	signal(SIGCHLD, SIG_IGN);
+	for (i = 0; i < num_pre_forks; i++) {
+		pid_t pid = fork();
+
+		SCX_FAIL_IF(pid < 0, "Failed to fork child");
+		if (pid == 0) {
+			char buf;
+
+			close(pipe_fds[1]);
+			if (read(pipe_fds[0], &buf, 1) < 0)
+				exit(1);
+			close(pipe_fds[0]);
+			exit(0);
+		}
+	}
+	close(pipe_fds[0]);
+
+	link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	/* Signal all pre-forked children to exit. */
+	close(pipe_fds[1]);
+	signal(SIGCHLD, SIG_DFL);
+
+	bpf_link__destroy(link);
+	SCX_GE(skel->bss->init_task_cnt, num_pre_forks);
+	SCX_GE(skel->bss->exit_task_cnt, num_pre_forks);
+
+	link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops);
+	SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+	/* SCHED_EXT children */
+	for (i = 0; i < num_children; i++) {
+		pids[i] = fork();
+		SCX_FAIL_IF(pids[i] < 0, "Failed to fork child");
+
+		if (pids[i] == 0) {
+			ret = sched_setscheduler(0, SCHED_EXT, &param);
+			SCX_BUG_ON(ret, "Failed to set sched to sched_ext");
+
+			/*
+			 * Reset to SCHED_OTHER for half of them. Counts for
+			 * everything should still be the same regardless, as
+			 * ops.disable() is invoked even if a task is still on
+			 * SCHED_EXT before it exits.
+			 */
+			if (i % 2 == 0) {
+				ret = sched_setscheduler(0, SCHED_OTHER, &param);
+				SCX_BUG_ON(ret, "Failed to reset sched to normal");
+			}
+			exit(0);
+		}
+	}
+	for (i = 0; i < num_children; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for SCX child\n");
+
+		SCX_FAIL_IF(status != 0, "SCX child %d exited with status %d\n", i,
+			    status);
+	}
+
+	/* SCHED_OTHER children */
+	for (i = 0; i < num_children; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0)
+			exit(0);
+	}
+
+	for (i = 0; i < num_children; i++) {
+		SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+			    "Failed to wait for normal child\n");
+
+		SCX_FAIL_IF(status != 0, "Normal child %d exited with status %d\n", i,
+			    status);
+	}
+
+	bpf_link__destroy(link);
+
+	SCX_GE(skel->bss->init_task_cnt, 2 * num_children);
+	SCX_GE(skel->bss->exit_task_cnt, 2 * num_children);
+
+	if (global) {
+		SCX_GE(skel->bss->enable_cnt, 2 * num_children);
+		SCX_GE(skel->bss->disable_cnt, 2 * num_children);
+	} else {
+		SCX_EQ(skel->bss->enable_cnt, num_children);
+		SCX_EQ(skel->bss->disable_cnt, num_children);
+	}
+	/*
+	 * We forked a ton of tasks before we attached the scheduler above, so
+	 * this should be fine. Technically it could be flaky if a ton of forks
+	 * are happening at the same time in other processes, but that should
+	 * be exceedingly unlikely.
+	 */
+	SCX_GT(skel->bss->init_transition_cnt, skel->bss->init_fork_cnt);
+	SCX_GE(skel->bss->init_fork_cnt, 2 * num_children);
+
+	init_enable_count__destroy(skel);
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	enum scx_test_status status;
+
+	status = run_test(true);
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	return run_test(false);
+}
+
+struct scx_test init_enable_count = {
+	.name = "init_enable_count",
+	.description = "Verify we correctly count the occurrences of init, "
+		       "enable, etc callbacks.",
+	.run = run,
+};
+REGISTER_SCX_TEST(&init_enable_count)

linux-7.2.3/tools/testing/selftests/sched_ext/maximal.bpf.c

@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler with every callback defined.
+ *
+ * This scheduler defines every callback.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define DSQ_ID 0
+
+s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
+		   u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
+{}
+
+void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_dsq_move_to_local(DSQ_ID, 0);
+}
+
+void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
+{}
+
+void BPF_STRUCT_OPS(maximal_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maximal_stopping, struct task_struct *p, bool runnable)
+{}
+
+void BPF_STRUCT_OPS(maximal_quiescent, struct task_struct *p, u64 deq_flags)
+{}
+
+bool BPF_STRUCT_OPS(maximal_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	return false;
+}
+
+bool BPF_STRUCT_OPS(maximal_core_sched_before, struct task_struct *a,
+		    struct task_struct *b)
+{
+	return false;
+}
+
+void BPF_STRUCT_OPS(maximal_set_weight, struct task_struct *p, u32 weight)
+{}
+
+void BPF_STRUCT_OPS(maximal_set_cpumask, struct task_struct *p,
+		    const struct cpumask *cpumask)
+{}
+
+void BPF_STRUCT_OPS(maximal_update_idle, s32 cpu, bool idle)
+{}
+
+SEC("tp_btf/sched_switch")
+int BPF_PROG(maximal_sched_switch, bool preempt, struct task_struct *prev,
+	     struct task_struct *next, unsigned int prev_state)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_cpu_online, s32 cpu)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_offline, s32 cpu)
+{}
+
+s32 BPF_STRUCT_OPS(maximal_init_task, struct task_struct *p,
+		   struct scx_init_task_args *args)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_enable, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maximal_exit_task, struct task_struct *p,
+		    struct scx_exit_task_args *args)
+{}
+
+void BPF_STRUCT_OPS(maximal_disable, struct task_struct *p)
+{}
+
+s32 BPF_STRUCT_OPS(maximal_cgroup_init, struct cgroup *cgrp,
+		   struct scx_cgroup_init_args *args)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_cgroup_exit, struct cgroup *cgrp)
+{}
+
+s32 BPF_STRUCT_OPS(maximal_cgroup_prep_move, struct task_struct *p,
+		   struct cgroup *from, struct cgroup *to)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_cgroup_move, struct task_struct *p,
+		    struct cgroup *from, struct cgroup *to)
+{}
+
+void BPF_STRUCT_OPS(maximal_cgroup_cancel_move, struct task_struct *p,
+	       struct cgroup *from, struct cgroup *to)
+{}
+
+void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
+{}
+
+void BPF_STRUCT_OPS(maximal_cgroup_set_bandwidth, struct cgroup *cgrp,
+		    u64 period_us, u64 quota_us, u64 burst_us)
+{}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
+{
+	return scx_bpf_create_dsq(DSQ_ID, -1);
+}
+
+void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
+{}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maximal_ops = {
+	.select_cpu		= (void *) maximal_select_cpu,
+	.enqueue		= (void *) maximal_enqueue,
+	.dequeue		= (void *) maximal_dequeue,
+	.dispatch		= (void *) maximal_dispatch,
+	.runnable		= (void *) maximal_runnable,
+	.running		= (void *) maximal_running,
+	.stopping		= (void *) maximal_stopping,
+	.quiescent		= (void *) maximal_quiescent,
+	.yield			= (void *) maximal_yield,
+	.core_sched_before	= (void *) maximal_core_sched_before,
+	.set_weight		= (void *) maximal_set_weight,
+	.set_cpumask		= (void *) maximal_set_cpumask,
+	.update_idle		= (void *) maximal_update_idle,
+	.cpu_online		= (void *) maximal_cpu_online,
+	.cpu_offline		= (void *) maximal_cpu_offline,
+	.init_task		= (void *) maximal_init_task,
+	.enable			= (void *) maximal_enable,
+	.exit_task		= (void *) maximal_exit_task,
+	.disable		= (void *) maximal_disable,
+	.cgroup_init		= (void *) maximal_cgroup_init,
+	.cgroup_exit		= (void *) maximal_cgroup_exit,
+	.cgroup_prep_move	= (void *) maximal_cgroup_prep_move,
+	.cgroup_move		= (void *) maximal_cgroup_move,
+	.cgroup_cancel_move	= (void *) maximal_cgroup_cancel_move,
+	.cgroup_set_weight	= (void *) maximal_cgroup_set_weight,
+	.cgroup_set_bandwidth	= (void *) maximal_cgroup_set_bandwidth,
+	.init			= (void *) maximal_init,
+	.exit			= (void *) maximal_exit,
+	.name			= "maximal",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/maximal.c

@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maximal.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct maximal *skel;
+
+	skel = maximal__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(maximal__load(skel), "Failed to load skel");
+
+	bpf_map__set_autoattach(skel->maps.maximal_ops, false);
+	SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct maximal *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.maximal_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct maximal *skel = ctx;
+
+	maximal__destroy(skel);
+}
+
+struct scx_test maximal = {
+	.name = "maximal",
+	.description = "Verify we can load a scheduler with every callback defined",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&maximal)

linux-7.2.3/tools/testing/selftests/sched_ext/maybe_null.bpf.c

@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maybe_null_success_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (p != NULL)
+		vtime_test = p->scx.dsq_vtime;
+}
+
+bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	if (to)
+		bpf_printk("Yielding to %s[%d]", to->comm, to->pid);
+
+	return false;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_success = {
+	.dispatch               = (void *) maybe_null_success_dispatch,
+	.yield			= (void *) maybe_null_success_yield,
+	.enable			= (void *) maybe_null_running,
+	.name			= "minimal",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/maybe_null.c

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maybe_null.bpf.skel.h"
+#include "maybe_null_fail_dsp.bpf.skel.h"
+#include "maybe_null_fail_yld.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status run(void *ctx)
+{
+	struct maybe_null *skel;
+	struct maybe_null_fail_dsp *fail_dsp;
+	struct maybe_null_fail_yld *fail_yld;
+
+	skel = maybe_null__open_and_load();
+	if (!skel) {
+		SCX_ERR("Failed to open and load maybe_null skel");
+		return SCX_TEST_FAIL;
+	}
+	maybe_null__destroy(skel);
+
+	fail_dsp = maybe_null_fail_dsp__open_and_load();
+	if (fail_dsp) {
+		maybe_null_fail_dsp__destroy(fail_dsp);
+		SCX_ERR("Should failed to open and load maybe_null_fail_dsp skel");
+		return SCX_TEST_FAIL;
+	}
+
+	fail_yld = maybe_null_fail_yld__open_and_load();
+	if (fail_yld) {
+		maybe_null_fail_yld__destroy(fail_yld);
+		SCX_ERR("Should failed to open and load maybe_null_fail_yld skel");
+		return SCX_TEST_FAIL;
+	}
+
+	return SCX_TEST_PASS;
+}
+
+struct scx_test maybe_null = {
+	.name = "maybe_null",
+	.description = "Verify if PTR_MAYBE_NULL works for .dispatch",
+	.run = run,
+};
+REGISTER_SCX_TEST(&maybe_null)

linux-7.2.3/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p)
+{
+	vtime_test = p->scx.dsq_vtime;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_fail = {
+	.dispatch               = (void *) maybe_null_fail_dispatch,
+	.enable			= (void *) maybe_null_running,
+	.name			= "maybe_null_fail_dispatch",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+u64 vtime_test;
+
+void BPF_STRUCT_OPS(maybe_null_running, struct task_struct *p)
+{}
+
+bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from,
+		    struct task_struct *to)
+{
+	bpf_printk("Yielding to %s[%d]", to->comm, to->pid);
+
+	return false;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maybe_null_fail = {
+	.yield			= (void *) maybe_null_fail_yield,
+	.enable			= (void *) maybe_null_running,
+	.name			= "maybe_null_fail_yield",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/minimal.bpf.c

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A completely minimal scheduler.
+ *
+ * This scheduler defines the absolute minimal set of struct sched_ext_ops
+ * fields: its name. It should _not_ fail to be loaded, and can be used to
+ * exercise the default scheduling paths in ext.c.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC(".struct_ops.link")
+struct sched_ext_ops minimal_ops = {
+	.name			= "minimal",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/minimal.c

@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "minimal.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct minimal *skel;
+
+	skel = minimal__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(minimal__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct minimal *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		return SCX_TEST_FAIL;
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct minimal *skel = ctx;
+
+	minimal__destroy(skel);
+}
+
+struct scx_test minimal = {
+	.name = "minimal",
+	.description = "Verify we can load a fully minimal scheduler",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&minimal)

linux-7.2.3/tools/testing/selftests/sched_ext/nohz_tick.bpf.c

@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+ *
+ * Exercise tick dependency transitions between infinite and finite slices.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu;
+bool finite_phase;
+u64 nr_inf_running;
+u64 nr_finite_running;
+u64 nr_finite_ticks;
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(nohz_tick_select_cpu, struct task_struct *p, s32 prev_cpu,
+		   u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(nohz_tick_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	u64 slice = finite_phase ? 1000000ULL : SCX_SLICE_INF;
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, slice, enq_flags);
+	if (enq_flags & SCX_ENQ_LAST)
+		scx_bpf_kick_cpu(test_cpu, SCX_KICK_IDLE);
+}
+
+void BPF_STRUCT_OPS(nohz_tick_running, struct task_struct *p)
+{
+	if (bpf_get_smp_processor_id() != test_cpu)
+		return;
+
+	if (finite_phase)
+		__sync_fetch_and_add(&nr_finite_running, 1);
+	else
+		__sync_fetch_and_add(&nr_inf_running, 1);
+}
+
+void BPF_STRUCT_OPS(nohz_tick_tick, struct task_struct *p)
+{
+	if (bpf_get_smp_processor_id() == test_cpu && finite_phase)
+		__sync_fetch_and_add(&nr_finite_ticks, 1);
+}
+
+void BPF_STRUCT_OPS(nohz_tick_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops nohz_tick_ops = {
+	.select_cpu		= (void *)nohz_tick_select_cpu,
+	.enqueue		= (void *)nohz_tick_enqueue,
+	.running		= (void *)nohz_tick_running,
+	.tick			= (void *)nohz_tick_tick,
+	.exit			= (void *)nohz_tick_exit,
+	.name			= "nohz_tick",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/nohz_tick.c

@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+ *
+ * Validate that a finite-slice EXT task restarts the scheduler tick when it
+ * follows an infinite-slice EXT task and an idle interval on a NOHZ_FULL CPU.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include <scx/common.h>
+
+#include "nohz_tick.bpf.skel.h"
+#include "scx_test.h"
+
+#ifndef SCHED_EXT
+#define SCHED_EXT 7
+#endif
+
+#define MIN_FINITE_TICKS 3
+#define PHASE_TIMEOUT_MS 1000
+
+struct nohz_tick_ctx {
+	struct nohz_tick *skel;
+	cpu_set_t original_mask;
+	int test_cpu;
+};
+
+static int first_allowed_cpu(const cpu_set_t *mask, int first, int last)
+{
+	int cpu;
+
+	for (cpu = first; cpu <= last && cpu < CPU_SETSIZE; cpu++)
+		if (CPU_ISSET(cpu, mask))
+			return cpu;
+
+	return -1;
+}
+
+static int find_nohz_full_cpu(const cpu_set_t *allowed)
+{
+	char buf[4096], *cur, *end;
+	FILE *file;
+
+	file = fopen("/sys/devices/system/cpu/nohz_full", "r");
+	if (!file)
+		return -1;
+	if (!fgets(buf, sizeof(buf), file)) {
+		fclose(file);
+		return -1;
+	}
+	fclose(file);
+
+	cur = buf;
+	while (*cur) {
+		long first, last;
+		int cpu;
+
+		while (*cur == ' ' || *cur == '\t' || *cur == ',')
+			cur++;
+		if (*cur < '0' || *cur > '9')
+			break;
+
+		errno = 0;
+		first = strtol(cur, &end, 10);
+		if (errno || end == cur || first < 0 || first >= CPU_SETSIZE)
+			return -1;
+		cur = end;
+		last = first;
+		if (*cur == '-') {
+			cur++;
+			errno = 0;
+			last = strtol(cur, &end, 10);
+			if (errno || end == cur || last < first)
+				return -1;
+			cur = end;
+		}
+
+		cpu = first_allowed_cpu(allowed, first, last);
+		if (cpu >= 0)
+			return cpu;
+	}
+
+	return -1;
+}
+
+static pid_t start_worker(int cpu)
+{
+	struct sched_param param = {};
+	cpu_set_t mask;
+	pid_t parent;
+	pid_t pid;
+
+	parent = getpid();
+	pid = fork();
+	if (pid != 0)
+		return pid;
+	if (prctl(PR_SET_PDEATHSIG, SIGKILL) || getppid() != parent)
+		_exit(1);
+
+	/*
+	 * Become EXT before touching the target so it stays idle until wakeup.
+	 */
+	if (sched_setscheduler(0, SCHED_EXT, &param))
+		_exit(1);
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	if (sched_setaffinity(0, sizeof(mask), &mask))
+		_exit(1);
+
+	for (;;)
+		asm volatile("" ::: "memory");
+}
+
+static void stop_worker(pid_t pid)
+{
+	if (pid <= 0)
+		return;
+
+	kill(pid, SIGKILL);
+	waitpid(pid, NULL, 0);
+}
+
+static int pause_worker(pid_t pid)
+{
+	int status;
+
+	if (kill(pid, SIGSTOP))
+		return -errno;
+	if (waitpid(pid, &status, WUNTRACED) != pid)
+		return -errno;
+	if (!WIFSTOPPED(status))
+		return -ECHILD;
+
+	return 0;
+}
+
+static bool wait_for_counter(const u64 *counter, u64 value, int timeout_ms)
+{
+	int elapsed;
+
+	for (elapsed = 0; elapsed < timeout_ms; elapsed++) {
+		if (__atomic_load_n(counter, __ATOMIC_RELAXED) >= value)
+			return true;
+		usleep(1000);
+	}
+
+	return false;
+}
+
+static enum scx_test_status setup(void **ctx_ptr)
+{
+	struct nohz_tick_ctx *ctx;
+	cpu_set_t controller_mask;
+	int cpu;
+
+	ctx = calloc(1, sizeof(*ctx));
+	SCX_FAIL_IF(!ctx, "Failed to allocate context");
+	if (sched_getaffinity(0, sizeof(ctx->original_mask),
+			      &ctx->original_mask)) {
+		free(ctx);
+		SCX_FAIL("Failed to get affinity (%d)", errno);
+	}
+
+	cpu = find_nohz_full_cpu(&ctx->original_mask);
+	if (cpu < 0) {
+		fprintf(stderr, "SKIP: no allowed NOHZ_FULL CPU\n");
+		free(ctx);
+		return SCX_TEST_SKIP;
+	}
+
+	controller_mask = ctx->original_mask;
+	CPU_CLR(cpu, &controller_mask);
+	if (CPU_COUNT(&controller_mask) == 0) {
+		fprintf(stderr, "SKIP: no housekeeping CPU available\n");
+		free(ctx);
+		return SCX_TEST_SKIP;
+	}
+
+	ctx->test_cpu = cpu;
+	ctx->skel = nohz_tick__open();
+	if (!ctx->skel) {
+		free(ctx);
+		SCX_FAIL("Failed to open skeleton");
+	}
+
+	SCX_ENUM_INIT(ctx->skel);
+	ctx->skel->rodata->test_cpu = cpu;
+	ctx->skel->struct_ops.nohz_tick_ops->flags |= SCX_OPS_SWITCH_PARTIAL |
+							   SCX_OPS_ENQ_LAST;
+	if (nohz_tick__load(ctx->skel)) {
+		nohz_tick__destroy(ctx->skel);
+		free(ctx);
+		SCX_FAIL("Failed to load skeleton");
+	}
+
+	if (sched_setaffinity(0, sizeof(controller_mask), &controller_mask)) {
+		nohz_tick__destroy(ctx->skel);
+		free(ctx);
+		SCX_FAIL("Failed to move controller off CPU %d (%d)", cpu, errno);
+	}
+
+	*ctx_ptr = ctx;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx_ptr)
+{
+	struct nohz_tick_ctx *ctx = ctx_ptr;
+	struct nohz_tick *skel = ctx->skel;
+	struct bpf_link *link = NULL;
+	enum scx_test_status status = SCX_TEST_FAIL;
+	pid_t finite_worker = -1;
+	pid_t inf_worker = -1;
+	u64 finite_running;
+	u64 finite_ticks;
+	int ret;
+
+	link = bpf_map__attach_struct_ops(skel->maps.nohz_tick_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		goto out;
+	}
+
+	/*
+	 * Establish SCX_RQ_CAN_STOP_TICK with an infinite-slice task.
+	 */
+	inf_worker = start_worker(ctx->test_cpu);
+	if (inf_worker < 0) {
+		SCX_ERR("Failed to start infinite-slice worker (%d)", errno);
+		goto out;
+	}
+	if (!wait_for_counter(&skel->bss->nr_inf_running, 1,
+			      PHASE_TIMEOUT_MS)) {
+		SCX_ERR("Infinite-slice worker was not scheduled");
+		goto out;
+	}
+
+	/* Block without exiting so the rq retains the infinite-slice state. */
+	ret = pause_worker(inf_worker);
+	if (ret) {
+		SCX_ERR("Failed to stop infinite-slice worker (%d)", ret);
+		goto out;
+	}
+
+	/* Let the target enter idle with its tick stopped. */
+	usleep(100000);
+
+	/*
+	 * The next EXT task receives a finite slice and must restart the tick.
+	 */
+	__atomic_store_n(&skel->bss->finite_phase, true, __ATOMIC_RELEASE);
+	finite_worker = start_worker(ctx->test_cpu);
+	if (finite_worker < 0) {
+		SCX_ERR("Failed to start finite-slice worker (%d)", errno);
+		goto out;
+	}
+	if (!wait_for_counter(&skel->bss->nr_finite_running, 1,
+			      PHASE_TIMEOUT_MS)) {
+		SCX_ERR("Finite-slice worker was not scheduled");
+		goto out;
+	}
+	if (!wait_for_counter(&skel->bss->nr_finite_ticks, MIN_FINITE_TICKS,
+			      PHASE_TIMEOUT_MS)) {
+		SCX_ERR("Finite-slice worker received only %llu scheduler ticks",
+			(unsigned long long)skel->bss->nr_finite_ticks);
+		goto out;
+	}
+	stop_worker(finite_worker);
+	finite_worker = -1;
+
+	/*
+	 * Leave the CPU idle after a finite-slice task. The next finite-slice
+	 * task must restart the tick even though the slice type is unchanged.
+	 */
+	usleep(100000);
+	finite_running = __atomic_load_n(&skel->bss->nr_finite_running,
+					 __ATOMIC_RELAXED);
+	finite_ticks = __atomic_load_n(&skel->bss->nr_finite_ticks,
+				       __ATOMIC_RELAXED);
+
+	finite_worker = start_worker(ctx->test_cpu);
+	if (finite_worker < 0) {
+		SCX_ERR("Failed to start second finite-slice worker (%d)", errno);
+		goto out;
+	}
+	if (!wait_for_counter(&skel->bss->nr_finite_running,
+			      finite_running + 1, PHASE_TIMEOUT_MS)) {
+		SCX_ERR("Second finite-slice worker was not scheduled");
+		goto out;
+	}
+	if (!wait_for_counter(&skel->bss->nr_finite_ticks,
+			      finite_ticks + MIN_FINITE_TICKS,
+			      PHASE_TIMEOUT_MS)) {
+		SCX_ERR("Second finite-slice worker received only %llu scheduler ticks",
+			(unsigned long long)(skel->bss->nr_finite_ticks -
+					     finite_ticks));
+		goto out;
+	}
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		goto out;
+	}
+
+	fprintf(stderr, "CPU %d received %llu finite-slice ticks\n",
+		ctx->test_cpu,
+		(unsigned long long)skel->bss->nr_finite_ticks);
+	status = SCX_TEST_PASS;
+out:
+	stop_worker(finite_worker);
+	stop_worker(inf_worker);
+	if (link)
+		bpf_link__destroy(link);
+	return status;
+}
+
+static void cleanup(void *ctx_ptr)
+{
+	struct nohz_tick_ctx *ctx = ctx_ptr;
+
+	sched_setaffinity(0, sizeof(ctx->original_mask), &ctx->original_mask);
+	nohz_tick__destroy(ctx->skel);
+	free(ctx);
+}
+
+struct scx_test nohz_tick = {
+	.name = "nohz_tick",
+	.description = "Verify finite EXT slices restart the NOHZ_FULL tick",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&nohz_tick)

linux-7.2.3/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.bpf.c

@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are
+ * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs,
+ * such as TCP congestion control programs, should be rejected by the BPF
+ * verifier when attempting to call these kfuncs.
+ *
+ * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
+ * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com>
+ */
+
+#include <scx/common.bpf.h>
+
+SEC("struct_ops/ssthresh")
+__u32 BPF_PROG(tcp_ca_ssthresh, struct sock *sk)
+{
+	/*
+	 * This call should be rejected by the verifier because this is a
+	 * TCP congestion control program (non-SCX struct_ops).
+	 */
+	scx_bpf_kick_cpu(0, 0);
+	return 2;
+}
+
+SEC("struct_ops/cong_avoid")
+void BPF_PROG(tcp_ca_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) {}
+
+SEC("struct_ops/undo_cwnd")
+__u32 BPF_PROG(tcp_ca_undo_cwnd, struct sock *sk) { return 2; }
+
+SEC(".struct_ops")
+struct tcp_congestion_ops tcp_non_scx_ca = {
+	.ssthresh   = (void *)tcp_ca_ssthresh,
+	.cong_avoid = (void *)tcp_ca_cong_avoid,
+	.undo_cwnd  = (void *)tcp_ca_undo_cwnd,
+	.name       = "tcp_kfunc_deny",
+};
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/tools/testing/selftests/sched_ext/non_scx_kfunc_deny.c

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Verify that context-sensitive SCX kfuncs (even "unlocked" ones) are
+ * restricted to only SCX struct_ops programs. Non-SCX struct_ops programs,
+ * such as TCP congestion control programs, should be rejected by the BPF
+ * verifier when attempting to call these kfuncs.
+ *
+ * Copyright (C) 2026 Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
+ * Copyright (C) 2026 Cheng-Yang Chou <yphbchou0911@gmail.com>
+ */
+
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+#include "non_scx_kfunc_deny.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status run(void *ctx)
+{
+	struct non_scx_kfunc_deny *skel;
+	int err;
+
+	skel = non_scx_kfunc_deny__open();
+	if (!skel) {
+		SCX_ERR("Failed to open skel");
+		return SCX_TEST_FAIL;
+	}
+
+	err = non_scx_kfunc_deny__load(skel);
+	non_scx_kfunc_deny__destroy(skel);
+
+	if (err == 0) {
+		SCX_ERR("non-SCX BPF program loaded when it should have been rejected");
+		return SCX_TEST_FAIL;
+	}
+
+	return SCX_TEST_PASS;
+}
+
+struct scx_test non_scx_kfunc_deny = {
+	.name = "non_scx_kfunc_deny",
+	.description = "Verify that non-SCX struct_ops programs cannot call SCX kfuncs",
+	.run = run,
+};
+REGISTER_SCX_TEST(&non_scx_kfunc_deny)

linux-7.2.3/tools/testing/selftests/sched_ext/numa.bpf.c

@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that validates the behavior of the NUMA-aware
+ * functionalities.
+ *
+ * The scheduler creates a separate DSQ for each NUMA node, ensuring tasks
+ * are exclusively processed by CPUs within their respective nodes. Idle
+ * CPUs are selected only within the same node, so task migration can only
+ * occurs between CPUs belonging to the same node.
+ *
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+const volatile unsigned int __COMPAT_SCX_PICK_IDLE_IN_NODE;
+
+static bool is_cpu_idle(s32 cpu, int node)
+{
+	const struct cpumask *idle_cpumask;
+	bool idle;
+
+	idle_cpumask = __COMPAT_scx_bpf_get_idle_cpumask_node(node);
+	idle = bpf_cpumask_test_cpu(cpu, idle_cpumask);
+	scx_bpf_put_cpumask(idle_cpumask);
+
+	return idle;
+}
+
+s32 BPF_STRUCT_OPS(numa_select_cpu,
+		   struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	s32 task_cpu = scx_bpf_task_cpu(p);
+	int node = __COMPAT_scx_bpf_cpu_node(task_cpu);
+	s32 cpu;
+
+	/*
+	 * We could just use __COMPAT_scx_bpf_pick_any_cpu_node() here,
+	 * since it already tries to pick an idle CPU within the node
+	 * first, but let's use both functions for better testing coverage.
+	 */
+	cpu = __COMPAT_scx_bpf_pick_idle_cpu_node(p->cpus_ptr, node,
+					__COMPAT_SCX_PICK_IDLE_IN_NODE);
+	if (cpu < 0)
+		cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node,
+						__COMPAT_SCX_PICK_IDLE_IN_NODE);
+
+	/*
+	 * @task_cpu may be outside of p->cpus_ptr if @p's affinity
+	 * changed while it was sleeping. This means it's possible for
+	 * p->cpus_ptr to not include any CPUs from @node.
+	 * If we failed to find a cpu in @node, check if @task_cpu
+	 * is outside of p->cpus_ptr and just return @prev_cpu if it is.
+	 */
+	if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr))
+		return prev_cpu;
+
+	if (is_cpu_idle(cpu, node))
+		scx_bpf_error("CPU %d should be marked as busy", cpu);
+
+	if (__COMPAT_scx_bpf_cpu_node(cpu) != node)
+		scx_bpf_error("CPU %d should be in node %d", cpu, node);
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(numa_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p));
+
+	scx_bpf_dsq_insert(p, node, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(numa_dispatch, s32 cpu, struct task_struct *prev)
+{
+	int node = __COMPAT_scx_bpf_cpu_node(cpu);
+
+	scx_bpf_dsq_move_to_local(node, 0);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(numa_init)
+{
+	int node, err;
+
+	bpf_for(node, 0, __COMPAT_scx_bpf_nr_node_ids()) {
+		err = scx_bpf_create_dsq(node, node);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(numa_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops numa_ops = {
+	.select_cpu		= (void *)numa_select_cpu,
+	.enqueue		= (void *)numa_enqueue,
+	.dispatch		= (void *)numa_dispatch,
+	.init			= (void *)numa_init,
+	.exit			= (void *)numa_exit,
+	.name			= "numa",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/numa.c

@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "numa.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct numa *skel;
+
+	skel = numa__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	skel->rodata->__COMPAT_SCX_PICK_IDLE_IN_NODE = SCX_PICK_IDLE_IN_NODE;
+	skel->struct_ops.numa_ops->flags = SCX_OPS_BUILTIN_IDLE_PER_NODE;
+	SCX_FAIL_IF(numa__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct numa *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.numa_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	/* Just sleeping is fine, plenty of scheduling events happening */
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct numa *skel = ctx;
+
+	numa__destroy(skel);
+}
+
+struct scx_test numa = {
+	.name = "numa",
+	.description = "Verify NUMA-aware functionalities",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&numa)

linux-7.2.3/tools/testing/selftests/sched_ext/peek_dsq.bpf.c

@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A BPF program for testing DSQ operations and peek in particular.
+ *
+ * Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2025 Ryan Newton <ryan.newton@alum.mit.edu>
+ */
+
+#include <scx/common.bpf.h>
+#include <scx/compat.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei); /* Error handling */
+
+#define MAX_SAMPLES 100
+#define MAX_CPUS 512
+#define DSQ_POOL_SIZE 8
+int max_samples = MAX_SAMPLES;
+int max_cpus = MAX_CPUS;
+int dsq_pool_size = DSQ_POOL_SIZE;
+
+/* Global variables to store test results */
+int dsq_peek_result1 = -1;
+long dsq_inserted_pid = -1;
+int insert_test_cpu = -1; /* Set to the cpu that performs the test */
+long dsq_peek_result2 = -1;
+long dsq_peek_result2_pid = -1;
+long dsq_peek_result2_expected = -1;
+int test_dsq_id = 1234; /* Use a simple ID like create_dsq example */
+int real_dsq_id = 1235; /* DSQ for normal operation */
+int enqueue_count = -1;
+int dispatch_count = -1;
+bool debug_ksym_exists;
+
+/* DSQ pool for stress testing */
+int dsq_pool_base_id = 2000;
+int phase1_complete = -1;
+long total_peek_attempts = -1;
+long successful_peeks = -1;
+
+/* BPF map for sharing peek results with userspace */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, MAX_SAMPLES);
+	__type(key, u32);
+	__type(value, long);
+} peek_results SEC(".maps");
+
+static int get_random_dsq_id(void)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	return dsq_pool_base_id + (time % DSQ_POOL_SIZE);
+}
+
+static void record_peek_result(long pid)
+{
+	u32 slot_key;
+	long *slot_pid_ptr;
+	u32 ix;
+
+	if (pid <= 0)
+		return;
+
+	/* Find an empty slot or one with the same PID */
+	bpf_for(ix, 0, 10) {
+		slot_key = ((u64)pid + ix) % MAX_SAMPLES;
+		slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key);
+		if (!slot_pid_ptr)
+			continue;
+
+		if (*slot_pid_ptr == -1 || *slot_pid_ptr == pid) {
+			*slot_pid_ptr = pid;
+			break;
+		}
+	}
+}
+
+/* Scan all DSQs in the pool and try to move a task to local */
+static int scan_dsq_pool(void)
+{
+	struct task_struct *task;
+	int moved = 0;
+	int i;
+
+	bpf_for(i, 0, DSQ_POOL_SIZE) {
+		int dsq_id = dsq_pool_base_id + i;
+
+		total_peek_attempts++;
+
+		task = __COMPAT_scx_bpf_dsq_peek(dsq_id);
+		if (task) {
+			successful_peeks++;
+			record_peek_result(task->pid);
+
+			/* Try to move this task to local */
+			if (!moved && scx_bpf_dsq_move_to_local(dsq_id, 0)) {
+				moved = 1;
+				break;
+			}
+		}
+	}
+	return moved;
+}
+
+/* Struct_ops scheduler for testing DSQ peek operations */
+void BPF_STRUCT_OPS(peek_dsq_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	struct task_struct *peek_result;
+	int last_insert_test_cpu, cpu;
+
+	enqueue_count++;
+	cpu = bpf_get_smp_processor_id();
+	last_insert_test_cpu = __sync_val_compare_and_swap(&insert_test_cpu, -1, cpu);
+
+	/* Phase 1: Simple insert-then-peek test (only on first task) */
+	if (last_insert_test_cpu == -1) {
+		bpf_printk("peek_dsq_enqueue beginning phase 1 peek test on cpu %d", cpu);
+
+		/* Test 1: Peek empty DSQ - should return NULL */
+		peek_result = __COMPAT_scx_bpf_dsq_peek(test_dsq_id);
+		dsq_peek_result1 = (long)peek_result; /* Should be 0 (NULL) */
+
+		/* Test 2: Insert task into test DSQ for testing in dispatch callback */
+		dsq_inserted_pid = p->pid;
+		scx_bpf_dsq_insert(p, test_dsq_id, 0, enq_flags);
+		dsq_peek_result2_expected = (long)p; /* Expected the task we just inserted */
+	} else if (!phase1_complete) {
+		/* Still in phase 1, use real DSQ */
+		scx_bpf_dsq_insert(p, real_dsq_id, 0, enq_flags);
+	} else {
+		/* Phase 2: Random DSQ insertion for stress testing */
+		int random_dsq_id = get_random_dsq_id();
+
+		scx_bpf_dsq_insert(p, random_dsq_id, 0, enq_flags);
+	}
+}
+
+void BPF_STRUCT_OPS(peek_dsq_dispatch, s32 cpu, struct task_struct *prev)
+{
+	dispatch_count++;
+
+	/* Phase 1: Complete the simple peek test if we inserted a task but
+	 * haven't tested peek yet
+	 */
+	if (insert_test_cpu == cpu && dsq_peek_result2 == -1) {
+		struct task_struct *peek_result;
+
+		bpf_printk("peek_dsq_dispatch completing phase 1 peek test on cpu %d", cpu);
+
+		/* Test 3: Peek DSQ after insert - should return the task we inserted */
+		peek_result = __COMPAT_scx_bpf_dsq_peek(test_dsq_id);
+		/* Store the PID of the peeked task for comparison */
+		dsq_peek_result2 = (long)peek_result;
+		dsq_peek_result2_pid = peek_result ? peek_result->pid : -1;
+
+		/* Now consume the task since we've peeked at it */
+		scx_bpf_dsq_move_to_local(test_dsq_id, 0);
+
+		/* Mark phase 1 as complete */
+		phase1_complete = 1;
+		bpf_printk("Phase 1 complete, starting phase 2 stress testing");
+	} else if (!phase1_complete) {
+		/* Still in phase 1, use real DSQ */
+		scx_bpf_dsq_move_to_local(real_dsq_id, 0);
+	} else {
+		/* Phase 2: Scan all DSQs in the pool and try to move a task */
+		if (!scan_dsq_pool()) {
+			/* No tasks found in DSQ pool, fall back to real DSQ */
+			scx_bpf_dsq_move_to_local(real_dsq_id, 0);
+		}
+	}
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(peek_dsq_init)
+{
+	s32 err;
+	int i;
+
+	/* Always set debug values so we can see which version we're using */
+	debug_ksym_exists = bpf_ksym_exists(scx_bpf_dsq_peek) ? 1 : 0;
+
+	/* Initialize state first */
+	insert_test_cpu = -1;
+	enqueue_count = 0;
+	dispatch_count = 0;
+	phase1_complete = 0;
+	total_peek_attempts = 0;
+	successful_peeks = 0;
+
+	/* Create the test and real DSQs */
+	err = scx_bpf_create_dsq(test_dsq_id, -1);
+	if (err) {
+		scx_bpf_error("Failed to create DSQ %d: %d", test_dsq_id, err);
+		return err;
+	}
+	err = scx_bpf_create_dsq(real_dsq_id, -1);
+	if (err) {
+		scx_bpf_error("Failed to create DSQ %d: %d", real_dsq_id, err);
+		return err;
+	}
+
+	/* Create the DSQ pool for stress testing */
+	bpf_for(i, 0, DSQ_POOL_SIZE) {
+		int dsq_id = dsq_pool_base_id + i;
+
+		err = scx_bpf_create_dsq(dsq_id, -1);
+		if (err) {
+			scx_bpf_error("Failed to create DSQ pool entry %d: %d", dsq_id, err);
+			return err;
+		}
+	}
+
+	/* Initialize the peek results map */
+	bpf_for(i, 0, MAX_SAMPLES) {
+		u32 key = i;
+		long pid = -1;
+
+		bpf_map_update_elem(&peek_results, &key, &pid, BPF_ANY);
+	}
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(peek_dsq_exit, struct scx_exit_info *ei)
+{
+	int i;
+
+	/* Destroy the primary DSQs */
+	scx_bpf_destroy_dsq(test_dsq_id);
+	scx_bpf_destroy_dsq(real_dsq_id);
+
+	/* Destroy the DSQ pool */
+	bpf_for(i, 0, DSQ_POOL_SIZE) {
+		int dsq_id = dsq_pool_base_id + i;
+
+		scx_bpf_destroy_dsq(dsq_id);
+	}
+
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops peek_dsq_ops = {
+	.enqueue = (void *)peek_dsq_enqueue,
+	.dispatch = (void *)peek_dsq_dispatch,
+	.init = (void *)peek_dsq_init,
+	.exit = (void *)peek_dsq_exit,
+	.name = "peek_dsq",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/peek_dsq.c

@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for DSQ operations including create, destroy, and peek operations.
+ *
+ * Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2025 Ryan Newton <ryan.newton@alum.mit.edu>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <string.h>
+#include <sched.h>
+#include "peek_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_WORKERS 4
+
+static bool workload_running = true;
+static pthread_t workload_threads[NUM_WORKERS];
+
+/**
+ * Background workload thread that sleeps and wakes rapidly to exercise
+ * the scheduler's enqueue operations and ensure DSQ operations get tested.
+ */
+static void *workload_thread_fn(void *arg)
+{
+	while (workload_running) {
+		/* Sleep for a very short time to trigger scheduler activity */
+		usleep(1000); /* 1ms sleep */
+		/* Yield to ensure we go through the scheduler */
+		sched_yield();
+	}
+	return NULL;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct peek_dsq *skel;
+
+	skel = peek_dsq__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(peek_dsq__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static int print_observed_pids(struct bpf_map *map, int max_samples, const char *dsq_name)
+{
+	long count = 0;
+
+	printf("Observed %s DSQ peek pids:\n", dsq_name);
+	for (int i = 0; i < max_samples; i++) {
+		long pid;
+		int err;
+
+		err = bpf_map_lookup_elem(bpf_map__fd(map), &i, &pid);
+		if (err == 0) {
+			if (pid == 0) {
+				printf("  Sample %d: NULL peek\n", i);
+			} else if (pid > 0) {
+				printf("  Sample %d: pid %ld\n", i, pid);
+				count++;
+			}
+		} else {
+			printf("  Sample %d: error reading pid (err=%d)\n", i, err);
+		}
+	}
+	printf("Observed ~%ld pids in the %s DSQ(s)\n", count, dsq_name);
+	return count;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct peek_dsq *skel = ctx;
+	bool failed = false;
+	int seconds = 3;
+	int err;
+
+	/* Enable the scheduler to test DSQ operations */
+	printf("Enabling scheduler to test DSQ insert operations...\n");
+
+	struct bpf_link *link =
+		bpf_map__attach_struct_ops(skel->maps.peek_dsq_ops);
+
+	if (!link) {
+		SCX_ERR("Failed to attach struct_ops");
+		return SCX_TEST_FAIL;
+	}
+
+	printf("Starting %d background workload threads...\n", NUM_WORKERS);
+	workload_running = true;
+	for (int i = 0; i < NUM_WORKERS; i++) {
+		err = pthread_create(&workload_threads[i], NULL, workload_thread_fn, NULL);
+		if (err) {
+			SCX_ERR("Failed to create workload thread %d: %s", i, strerror(err));
+			/* Stop already created threads */
+			workload_running = false;
+			for (int j = 0; j < i; j++)
+				pthread_join(workload_threads[j], NULL);
+			bpf_link__destroy(link);
+			return SCX_TEST_FAIL;
+		}
+	}
+
+	printf("Waiting for enqueue events.\n");
+	sleep(seconds);
+	while (skel->data->enqueue_count <= 0) {
+		printf(".");
+		fflush(stdout);
+		sleep(1);
+		seconds++;
+		if (seconds >= 30) {
+			printf("\n\u2717 Timeout waiting for enqueue events\n");
+			/* Stop workload threads and cleanup */
+			workload_running = false;
+			for (int i = 0; i < NUM_WORKERS; i++)
+				pthread_join(workload_threads[i], NULL);
+			bpf_link__destroy(link);
+			return SCX_TEST_FAIL;
+		}
+	}
+
+	workload_running = false;
+	for (int i = 0; i < NUM_WORKERS; i++) {
+		err = pthread_join(workload_threads[i], NULL);
+		if (err) {
+			SCX_ERR("Failed to join workload thread %d: %s", i, strerror(err));
+			bpf_link__destroy(link);
+			return SCX_TEST_FAIL;
+		}
+	}
+	printf("Background workload threads stopped.\n");
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+
+	/* Detach the scheduler */
+	bpf_link__destroy(link);
+
+	printf("Enqueue/dispatch count over %d seconds: %d / %d\n", seconds,
+		skel->data->enqueue_count, skel->data->dispatch_count);
+	printf("Debug: ksym_exists=%d\n",
+	       skel->bss->debug_ksym_exists);
+
+	/* Check DSQ insert result */
+	printf("DSQ insert test done on cpu: %d\n", skel->data->insert_test_cpu);
+	if (skel->data->insert_test_cpu != -1)
+		printf("\u2713 DSQ insert succeeded !\n");
+	else {
+		printf("\u2717 DSQ insert failed or not attempted\n");
+		failed = true;
+	}
+
+	/* Check DSQ peek results */
+	printf("  DSQ peek result 1 (before insert): %d\n",
+	       skel->data->dsq_peek_result1);
+	if (skel->data->dsq_peek_result1 == 0)
+		printf("\u2713 DSQ peek verification success: peek returned NULL!\n");
+	else {
+		printf("\u2717 DSQ peek verification failed\n");
+		failed = true;
+	}
+
+	printf("  DSQ peek result 2 (after insert): %ld\n",
+	       skel->data->dsq_peek_result2);
+	printf("  DSQ peek result 2, expected: %ld\n",
+	       skel->data->dsq_peek_result2_expected);
+	if (skel->data->dsq_peek_result2 ==
+	    skel->data->dsq_peek_result2_expected)
+		printf("\u2713 DSQ peek verification success: peek returned the inserted task!\n");
+	else {
+		printf("\u2717 DSQ peek verification failed\n");
+		failed = true;
+	}
+
+	printf("  Inserted test task -> pid: %ld\n", skel->data->dsq_inserted_pid);
+	printf("  DSQ peek result 2 -> pid: %ld\n", skel->data->dsq_peek_result2_pid);
+
+	int pid_count;
+
+	pid_count = print_observed_pids(skel->maps.peek_results,
+					skel->data->max_samples, "DSQ pool");
+	printf("Total non-null peek observations: %ld out of %ld\n",
+	       skel->data->successful_peeks, skel->data->total_peek_attempts);
+
+	if (skel->bss->debug_ksym_exists && pid_count == 0) {
+		printf("\u2717 DSQ pool test failed: no successful peeks in native mode\n");
+		failed = true;
+	}
+	if (skel->bss->debug_ksym_exists && pid_count > 0)
+		printf("\u2713 DSQ pool test success: observed successful peeks in native mode\n");
+
+	if (failed)
+		return SCX_TEST_FAIL;
+	else
+		return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct peek_dsq *skel = ctx;
+
+	if (workload_running) {
+		workload_running = false;
+		for (int i = 0; i < NUM_WORKERS; i++)
+			pthread_join(workload_threads[i], NULL);
+	}
+
+	peek_dsq__destroy(skel);
+}
+
+struct scx_test peek_dsq = {
+	.name = "peek_dsq",
+	.description =
+		"Test DSQ create/destroy operations and future peek functionality",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&peek_dsq)

linux-7.2.3/tools/testing/selftests/sched_ext/prog_run.bpf.c

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates that we can invoke sched_ext kfuncs in
+ * BPF_PROG_TYPE_SYSCALL programs.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+
+#include <scx/common.bpf.h>
+
+UEI_DEFINE(uei);
+
+char _license[] SEC("license") = "GPL";
+
+SEC("syscall")
+int BPF_PROG(prog_run_syscall)
+{
+	scx_bpf_create_dsq(0, -1);
+	scx_bpf_exit(0xdeadbeef, "Exited from PROG_RUN");
+	return 0;
+}
+
+void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops prog_run_ops = {
+	.exit			= (void *) prog_run_exit,
+	.name			= "prog_run",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/prog_run.c

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "prog_run.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct prog_run *skel;
+
+	skel = prog_run__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct prog_run *skel = ctx;
+	struct bpf_link *link;
+	int prog_fd, err = 0;
+
+	prog_fd = bpf_program__fd(skel->progs.prog_run_syscall);
+	if (prog_fd < 0) {
+		SCX_ERR("Failed to get BPF_PROG_RUN prog");
+		return SCX_TEST_FAIL;
+	}
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	link = bpf_map__attach_struct_ops(skel->maps.prog_run_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		close(prog_fd);
+		return SCX_TEST_FAIL;
+	}
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	SCX_EQ(err, 0);
+
+	/* Assumes uei.kind is written last */
+	while (skel->data->uei.kind == EXIT_KIND(SCX_EXIT_NONE))
+		sched_yield();
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG_BPF));
+	SCX_EQ(skel->data->uei.exit_code, 0xdeadbeef);
+	close(prog_fd);
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct prog_run *skel = ctx;
+
+	prog_run__destroy(skel);
+}
+
+struct scx_test prog_run = {
+	.name = "prog_run",
+	.description = "Verify we can call into a scheduler with BPF_PROG_RUN, and invoke kfuncs",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&prog_run)

linux-7.2.3/tools/testing/selftests/sched_ext/reload_loop.c

@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <pthread.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "maximal.bpf.skel.h"
+#include "scx_test.h"
+
+static struct maximal *skel;
+static pthread_t threads[2];
+
+bool force_exit = false;
+
+static enum scx_test_status setup(void **ctx)
+{
+	skel = maximal__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(maximal__load(skel), "Failed to load skel");
+
+	bpf_map__set_autoattach(skel->maps.maximal_ops, false);
+	SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel");
+
+	return SCX_TEST_PASS;
+}
+
+static void *do_reload_loop(void *arg)
+{
+	u32 i;
+
+	for (i = 0; i < 1024 && !force_exit; i++) {
+		struct bpf_link *link;
+
+		link = bpf_map__attach_struct_ops(skel->maps.maximal_ops);
+		if (link)
+			bpf_link__destroy(link);
+	}
+
+	return NULL;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	int err;
+	void *ret;
+
+	err = pthread_create(&threads[0], NULL, do_reload_loop, NULL);
+	SCX_FAIL_IF(err, "Failed to create thread 0");
+
+	err = pthread_create(&threads[1], NULL, do_reload_loop, NULL);
+	SCX_FAIL_IF(err, "Failed to create thread 1");
+
+	SCX_FAIL_IF(pthread_join(threads[0], &ret), "thread 0 failed");
+	SCX_FAIL_IF(pthread_join(threads[1], &ret), "thread 1 failed");
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	force_exit = true;
+	maximal__destroy(skel);
+}
+
+struct scx_test reload_loop = {
+	.name = "reload_loop",
+	.description = "Stress test loading and unloading schedulers repeatedly in a tight loop",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&reload_loop)

linux-7.2.3/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",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/rt_stall.c

@@ -0,0 +1,293 @@
+// 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 "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 */
+
+/* Signal the parent that setup is complete by writing to a pipe */
+static void signal_ready(int fd)
+{
+	char c = 1;
+
+	if (write(fd, &c, 1) != 1) {
+		perror("write to ready pipe");
+		exit(EXIT_FAILURE);
+	}
+	close(fd);
+}
+
+/* Wait for a child to signal readiness via a pipe */
+static void wait_ready(int fd)
+{
+	char c;
+
+	if (read(fd, &c, 1) != 1) {
+		perror("read from ready pipe");
+		exit(EXIT_FAILURE);
+	}
+	close(fd);
+}
+
+/* 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;
+
+	if (!__COMPAT_struct_has_field("rq", "ext_server")) {
+		fprintf(stderr, "SKIP: ext DL server not supported\n");
+		return SCX_TEST_SKIP;
+	}
+
+	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(bool is_ext)
+{
+	/*
+	 * We're expecting the EXT task to get around 5% of CPU time when
+	 * competing with the RT task (small 1% fluctuations are expected).
+	 *
+	 * However, the EXT task should get at least 4% of the CPU to prove
+	 * that the EXT deadline server is working correctly. A percentage
+	 * less than 4% indicates a bug where RT tasks can potentially
+	 * stall SCHED_EXT tasks, causing the test to fail.
+	 */
+	const float expected_min_ratio = 0.04; /* 4% */
+	const char *class_str = is_ext ? "EXT" : "FAIR";
+
+	float ext_runtime, rt_runtime, actual_ratio;
+	int ext_pid, rt_pid;
+	int ext_ready[2], rt_ready[2];
+
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	if (pipe(ext_ready) || pipe(rt_ready)) {
+		perror("pipe");
+		ksft_exit_fail();
+	}
+
+	/* Create and set up a EXT task */
+	ext_pid = fork();
+	if (ext_pid == 0) {
+		close(ext_ready[0]);
+		close(rt_ready[0]);
+		close(rt_ready[1]);
+		set_affinity(CORE_ID);
+		signal_ready(ext_ready[1]);
+		process_func();
+		exit(0);
+	} else if (ext_pid < 0) {
+		perror("fork task");
+		ksft_exit_fail();
+	}
+
+	/* Create an RT task */
+	rt_pid = fork();
+	if (rt_pid == 0) {
+		close(ext_ready[0]);
+		close(ext_ready[1]);
+		close(rt_ready[0]);
+		set_affinity(CORE_ID);
+		set_sched(SCHED_FIFO, 50);
+		signal_ready(rt_ready[1]);
+		process_func();
+		exit(0);
+	} else if (rt_pid < 0) {
+		perror("fork for RT task");
+		ksft_exit_fail();
+	}
+
+	/*
+	 * Wait for both children to complete their setup (affinity and
+	 * scheduling policy) before starting the measurement window.
+	 * This prevents flaky failures caused by the RT child's setup
+	 * time eating into the measurement period.
+	 */
+	close(ext_ready[1]);
+	close(rt_ready[1]);
+	wait_ready(ext_ready[0]);
+	wait_ready(rt_ready[0]);
+
+	/* Let the processes run for the specified time */
+	sleep(RUN_TIME);
+
+	/* Get runtime for the EXT task */
+	ext_runtime = get_process_runtime(ext_pid);
+	if (ext_runtime == -1)
+		ksft_exit_fail_msg("Error getting runtime for %s task (PID %d)\n",
+				   class_str, ext_pid);
+	ksft_print_msg("Runtime of %s task (PID %d) is %f seconds\n",
+		       class_str, ext_pid, ext_runtime);
+
+	/* Get runtime for the RT task */
+	rt_runtime = get_process_runtime(rt_pid);
+	if (rt_runtime == -1)
+		ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid);
+	ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime);
+
+	/* Kill the processes */
+	kill(ext_pid, SIGKILL);
+	kill(rt_pid, SIGKILL);
+	waitpid(ext_pid, NULL, 0);
+	waitpid(rt_pid, NULL, 0);
+
+	/* Verify that the scx task got enough runtime */
+	actual_ratio = ext_runtime / (ext_runtime + rt_runtime);
+	ksft_print_msg("%s task got %.2f%% of total runtime\n",
+		       class_str, actual_ratio * 100);
+
+	if (actual_ratio >= expected_min_ratio) {
+		ksft_test_result_pass("PASS: %s task got more than %.2f%% of runtime\n",
+				      class_str, expected_min_ratio * 100);
+		return true;
+	}
+	ksft_test_result_fail("FAIL: %s task got less than %.2f%% of runtime\n",
+			      class_str, expected_min_ratio * 100);
+	return false;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct rt_stall *skel = ctx;
+	struct bpf_link *link = NULL;
+	bool res;
+	int i;
+
+	/*
+	 * Test if the dl_server is working both with and without the
+	 * sched_ext scheduler attached.
+	 *
+	 * This ensures all the scenarios are covered:
+	 *   - fair_server stop -> ext_server start
+	 *   - ext_server stop -> fair_server stop
+	 */
+	for (i = 0; i < 4; i++) {
+		bool is_ext = i % 2;
+
+		if (is_ext) {
+			memset(&skel->data->uei, 0, sizeof(skel->data->uei));
+			link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops);
+			SCX_FAIL_IF(!link, "Failed to attach scheduler");
+		}
+		res = sched_stress_test(is_ext);
+		if (is_ext) {
+			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)

linux-7.2.3/tools/testing/selftests/sched_ext/runner.c

@@ -0,0 +1,255 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include "scx_test.h"
+
+const char help_fmt[] =
+"The runner for sched_ext tests.\n"
+"\n"
+"The runner is statically linked against all testcases, and runs them all serially.\n"
+"It's required for the testcases to be serial, as only a single host-wide sched_ext\n"
+"scheduler may be loaded at any given time."
+"\n"
+"Usage: %s [-t TEST] [-s] [-l] [-q]\n"
+"\n"
+"  -t TEST       Only run tests whose name includes this string\n"
+"  -s            Include print output for skipped tests\n"
+"  -l            List all available tests\n"
+"  -q            Don't print the test descriptions during run\n"
+"  -h            Display this help and exit\n";
+
+static volatile int exit_req;
+static bool quiet, print_skipped, list;
+
+#define MAX_SCX_TESTS 2048
+
+static struct scx_test __scx_tests[MAX_SCX_TESTS];
+static unsigned __scx_num_tests = 0;
+
+static void sigint_handler(int simple)
+{
+	exit_req = 1;
+}
+
+static void print_test_preamble(const struct scx_test *test, bool quiet)
+{
+	printf("===== START =====\n");
+	printf("TEST: %s\n", test->name);
+	if (!quiet)
+		printf("DESCRIPTION: %s\n", test->description);
+	printf("OUTPUT:\n");
+
+	/*
+	 * The tests may fork with the preamble buffered
+	 * in the children's stdout. Flush before the test
+	 * to avoid printing the message multiple times.
+	 */
+	fflush(stdout);
+	fflush(stderr);
+}
+
+static const char *status_to_result(enum scx_test_status status)
+{
+	switch (status) {
+	case SCX_TEST_PASS:
+	case SCX_TEST_SKIP:
+		return "ok";
+	case SCX_TEST_FAIL:
+		return "not ok";
+	default:
+		return "<UNKNOWN>";
+	}
+}
+
+static void print_test_result(const struct scx_test *test,
+			      enum scx_test_status status,
+			      unsigned int testnum)
+{
+	const char *result = status_to_result(status);
+	const char *directive = status == SCX_TEST_SKIP ? "SKIP " : "";
+
+	printf("%s %u %s # %s\n", result, testnum, test->name, directive);
+	printf("=====  END  =====\n");
+}
+
+static bool should_skip_test(const struct scx_test *test, const char * filter)
+{
+	return !strstr(test->name, filter);
+}
+
+static enum scx_test_status run_test(const struct scx_test *test)
+{
+	enum scx_test_status status;
+	void *context = NULL;
+
+	if (test->setup) {
+		status = test->setup(&context);
+		if (status != SCX_TEST_PASS)
+			return status;
+	}
+
+	status = test->run(context);
+
+	if (test->cleanup)
+		test->cleanup(context);
+
+	return status;
+}
+
+static bool test_valid(const struct scx_test *test)
+{
+	if (!test) {
+		fprintf(stderr, "NULL test detected\n");
+		return false;
+	}
+
+	if (!test->name) {
+		fprintf(stderr,
+			"Test with no name found. Must specify test name.\n");
+		return false;
+	}
+
+	if (!test->description) {
+		fprintf(stderr, "Test %s requires description.\n", test->name);
+		return false;
+	}
+
+	if (!test->run) {
+		fprintf(stderr, "Test %s has no run() callback\n", test->name);
+		return false;
+	}
+
+	return true;
+}
+
+int main(int argc, char **argv)
+{
+	const char *filter = NULL;
+	const char *failed_tests[MAX_SCX_TESTS];
+	const char *skipped_tests[MAX_SCX_TESTS];
+	unsigned testnum = 0, i;
+	unsigned passed = 0, skipped = 0, failed = 0;
+	int opt;
+
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
+	while ((opt = getopt(argc, argv, "qslt:h")) != -1) {
+		switch (opt) {
+		case 'q':
+			quiet = true;
+			break;
+		case 's':
+			print_skipped = true;
+			break;
+		case 'l':
+			list = true;
+			break;
+		case 't':
+			filter = optarg;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	if (optind < argc) {
+		fprintf(stderr, "Unexpected argument '%s'. Use -t to filter tests.\n",
+			argv[optind]);
+		return 1;
+	}
+
+	if (filter) {
+		for (i = 0; i < __scx_num_tests; i++) {
+			if (!should_skip_test(&__scx_tests[i], filter))
+				break;
+		}
+		if (i == __scx_num_tests) {
+			fprintf(stderr, "No tests matched filter '%s'\n", filter);
+			fprintf(stderr, "Available tests (use -l to list):\n");
+			for (i = 0; i < __scx_num_tests; i++)
+				fprintf(stderr, "  %s\n", __scx_tests[i].name);
+			return 1;
+		}
+	}
+
+	for (i = 0; i < __scx_num_tests; i++) {
+		enum scx_test_status status;
+		struct scx_test *test = &__scx_tests[i];
+
+		if (exit_req)
+			break;
+
+		if (list) {
+			printf("%s\n", test->name);
+			if (i == (__scx_num_tests - 1))
+				return 0;
+			continue;
+		}
+
+		if (filter && should_skip_test(test, filter)) {
+			/*
+			 * Printing the skipped tests and their preambles can
+			 * add a lot of noise to the runner output. Printing
+			 * this is only really useful for CI, so let's skip it
+			 * by default.
+			 */
+			if (print_skipped) {
+				print_test_preamble(test, quiet);
+				print_test_result(test, SCX_TEST_SKIP, ++testnum);
+			}
+			continue;
+		}
+
+		print_test_preamble(test, quiet);
+		status = run_test(test);
+		print_test_result(test, status, ++testnum);
+		switch (status) {
+		case SCX_TEST_PASS:
+			passed++;
+			break;
+		case SCX_TEST_SKIP:
+			skipped_tests[skipped++] = test->name;
+			break;
+		case SCX_TEST_FAIL:
+			failed_tests[failed++] = test->name;
+			break;
+		}
+	}
+	printf("\n\n=============================\n\n");
+	printf("RESULTS:\n\n");
+	printf("PASSED:  %u\n", passed);
+	printf("SKIPPED: %u\n", skipped);
+	printf("FAILED:  %u\n", failed);
+	if (skipped > 0) {
+		printf("\nSkipped tests:\n");
+		for (i = 0; i < skipped; i++)
+			printf("  - %s\n", skipped_tests[i]);
+	}
+	if (failed > 0) {
+		printf("\nFailed tests:\n");
+		for (i = 0; i < failed; i++)
+			printf("  - %s\n", failed_tests[i]);
+	}
+
+	return failed > 0 ? 1 : 0;
+}
+
+void scx_test_register(struct scx_test *test)
+{
+	SCX_BUG_ON(!test_valid(test), "Invalid test found");
+	SCX_BUG_ON(__scx_num_tests >= MAX_SCX_TESTS, "Maximum tests exceeded");
+
+	__scx_tests[__scx_num_tests++] = *test;
+}

linux-7.2.3/tools/testing/selftests/sched_ext/scx_test.h

@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ */
+
+#ifndef __SCX_TEST_H__
+#define __SCX_TEST_H__
+
+#include <errno.h>
+#include <scx/common.h>
+#include <scx/compat.h>
+
+enum scx_test_status {
+	SCX_TEST_PASS = 0,
+	SCX_TEST_SKIP,
+	SCX_TEST_FAIL,
+};
+
+#define EXIT_KIND(__ent) __COMPAT_ENUM_OR_ZERO("scx_exit_kind", #__ent)
+
+struct scx_test {
+	/**
+	 * name - The name of the testcase.
+	 */
+	const char *name;
+
+	/**
+	 * description - A description of your testcase: what it tests and is
+	 * meant to validate.
+	 */
+	const char *description;
+
+	/*
+	 * setup - Setup the test.
+	 * @ctx: A pointer to a context object that will be passed to run and
+	 *	 cleanup.
+	 *
+	 * An optional callback that allows a testcase to perform setup for its
+	 * run. A test may return SCX_TEST_SKIP to skip the run.
+	 */
+	enum scx_test_status (*setup)(void **ctx);
+
+	/*
+	 * run - Run the test.
+	 * @ctx: Context set in the setup() callback. If @ctx was not set in
+	 *	 setup(), it is NULL.
+	 *
+	 * The main test. Callers should return one of:
+	 *
+	 * - SCX_TEST_PASS: Test passed
+	 * - SCX_TEST_SKIP: Test should be skipped
+	 * - SCX_TEST_FAIL: Test failed
+	 *
+	 * This callback must be defined.
+	 */
+	enum scx_test_status (*run)(void *ctx);
+
+	/*
+	 * cleanup - Perform cleanup following the test
+	 * @ctx: Context set in the setup() callback. If @ctx was not set in
+	 *	 setup(), it is NULL.
+	 *
+	 * An optional callback that allows a test to perform cleanup after
+	 * being run. This callback is run even if the run() callback returns
+	 * SCX_TEST_SKIP or SCX_TEST_FAIL. It is not run if setup() returns
+	 * SCX_TEST_SKIP or SCX_TEST_FAIL.
+	 */
+	void (*cleanup)(void *ctx);
+};
+
+void scx_test_register(struct scx_test *test);
+
+#define REGISTER_SCX_TEST(__test)			\
+	__attribute__((constructor))			\
+	static void ___scxregister##__LINE__(void)	\
+	{						\
+		scx_test_register(__test);		\
+	}
+
+#define SCX_ERR(__fmt, ...)						\
+	do {								\
+		fprintf(stderr, "ERR: %s:%d\n", __FILE__, __LINE__);	\
+		fprintf(stderr, __fmt"\n", ##__VA_ARGS__);			\
+	} while (0)
+
+#define SCX_FAIL(__fmt, ...)						\
+	do {								\
+		SCX_ERR(__fmt, ##__VA_ARGS__);				\
+		return SCX_TEST_FAIL;					\
+	} while (0)
+
+#define SCX_FAIL_IF(__cond, __fmt, ...)					\
+	do {								\
+		if (__cond)						\
+			SCX_FAIL(__fmt, ##__VA_ARGS__);			\
+	} while (0)
+
+#define SCX_GT(_x, _y) SCX_FAIL_IF((_x) <= (_y), "Expected %s > %s (%lu > %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_GE(_x, _y) SCX_FAIL_IF((_x) < (_y), "Expected %s >= %s (%lu >= %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_LT(_x, _y) SCX_FAIL_IF((_x) >= (_y), "Expected %s < %s (%lu < %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_LE(_x, _y) SCX_FAIL_IF((_x) > (_y), "Expected %s <= %s (%lu <= %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_EQ(_x, _y) SCX_FAIL_IF((_x) != (_y), "Expected %s == %s (%lu == %lu)",	\
+				   #_x, #_y, (u64)(_x), (u64)(_y))
+#define SCX_ASSERT(_x) SCX_FAIL_IF(!(_x), "Expected %s to be true (%lu)",		\
+				   #_x, (u64)(_x))
+
+#define SCX_ECODE_VAL(__ecode) ({						\
+        u64 __val = 0;								\
+	bool __found = false;							\
+										\
+	__found = __COMPAT_read_enum("scx_exit_code", #__ecode, &__val);	\
+	SCX_ASSERT(__found);							\
+	(s64)__val;								\
+})
+
+#define SCX_KIND_VAL(__kind) ({							\
+        u64 __val = 0;								\
+	bool __found = false;							\
+										\
+	__found = __COMPAT_read_enum("scx_exit_kind", #__kind, &__val);		\
+	SCX_ASSERT(__found);							\
+	__val;									\
+})
+
+#endif  // # __SCX_TEST_H__

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c

@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+bool saw_local = false;
+
+static bool task_is_test(const struct task_struct *p)
+{
+	return !bpf_strncmp(p->comm, 9, "select_cpu");
+}
+
+void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	const struct cpumask *idle_mask = scx_bpf_get_idle_cpumask();
+
+	if (task_is_test(p) &&
+	    bpf_cpumask_test_cpu(scx_bpf_task_cpu(p), idle_mask)) {
+		saw_local = true;
+	}
+	scx_bpf_put_idle_cpumask(idle_mask);
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dfl_ops = {
+	.enqueue		= (void *) select_cpu_dfl_enqueue,
+	.name			= "select_cpu_dfl",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dfl.c

@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <stdlib.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dfl.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+struct select_cpu_dfl_ctx {
+	struct select_cpu_dfl	*skel;
+	struct bpf_link		*link;
+};
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dfl_ctx *tctx;
+
+	tctx = malloc(sizeof(*tctx));
+	SCX_FAIL_IF(!tctx, "Failed to allocate test context");
+	tctx->link = NULL;
+
+	tctx->skel = select_cpu_dfl__open();
+	if (!tctx->skel) {
+		free(tctx);
+		SCX_FAIL("Failed to open");
+	}
+	SCX_ENUM_INIT(tctx->skel);
+	if (select_cpu_dfl__load(tctx->skel)) {
+		select_cpu_dfl__destroy(tctx->skel);
+		free(tctx);
+		SCX_FAIL("Failed to load skel");
+	}
+
+	*ctx = tctx;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dfl_ctx *tctx = ctx;
+	pid_t pids[NUM_CHILDREN];
+	int i, status, nforked = 0;
+
+	tctx->link = bpf_map__attach_struct_ops(tctx->skel->maps.select_cpu_dfl_ops);
+	SCX_FAIL_IF(!tctx->link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+		if (pids[i] > 0)
+			nforked++;
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		if (pids[i] <= 0)
+			continue;
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	SCX_GT(nforked, 0);
+	SCX_ASSERT(!tctx->skel->bss->saw_local);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dfl_ctx *tctx = ctx;
+
+	if (tctx->link)
+		bpf_link__destroy(tctx->link);
+	select_cpu_dfl__destroy(tctx->skel);
+	free(tctx);
+}
+
+struct scx_test select_cpu_dfl = {
+	.name = "select_cpu_dfl",
+	.description = "Verify the default ops.select_cpu() dispatches tasks "
+		       "when idles cores are found, and skips ops.enqueue()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dfl)

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c

@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation, and with the SCX_OPS_ENQ_DFL_NO_DISPATCH ops flag
+ * specified.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+bool saw_local = false;
+
+/* Per-task scheduling context */
+struct task_ctx {
+	bool	force_local;	/* CPU changed by ops.select_cpu() */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct task_ctx);
+} task_ctx_stor SEC(".maps");
+
+/* Manually specify the signature until the kfunc is added to the scx repo. */
+s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+			   bool *found) __ksym;
+
+s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	struct task_ctx *tctx;
+	s32 cpu;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return -ESRCH;
+	}
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags,
+				     &tctx->force_local);
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	u64 dsq_id = SCX_DSQ_GLOBAL;
+	struct task_ctx *tctx;
+
+	tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+	if (!tctx) {
+		scx_bpf_error("task_ctx lookup failed");
+		return;
+	}
+
+	if (tctx->force_local) {
+		dsq_id = SCX_DSQ_LOCAL;
+		tctx->force_local = false;
+		saw_local = true;
+	}
+
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+}
+
+s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
+		   struct task_struct *p, struct scx_init_task_args *args)
+{
+	if (bpf_task_storage_get(&task_ctx_stor, p, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return 0;
+	else
+		return -ENOMEM;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dfl_nodispatch_ops = {
+	.select_cpu		= (void *) select_cpu_dfl_nodispatch_select_cpu,
+	.enqueue		= (void *) select_cpu_dfl_nodispatch_enqueue,
+	.init_task		= (void *) select_cpu_dfl_nodispatch_init_task,
+	.name			= "select_cpu_dfl_nodispatch",
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c

@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dfl_nodispatch.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel;
+
+	skel = select_cpu_dfl_nodispatch__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel = ctx;
+	struct bpf_link *link;
+	pid_t pids[NUM_CHILDREN];
+	int i, status;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dfl_nodispatch_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	SCX_ASSERT(skel->bss->saw_local);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dfl_nodispatch *skel = ctx;
+
+	select_cpu_dfl_nodispatch__destroy(skel);
+}
+
+struct scx_test select_cpu_dfl_nodispatch = {
+	.name = "select_cpu_dfl_nodispatch",
+	.description = "Verify behavior of scx_bpf_select_cpu_dfl() in "
+		       "ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dfl_nodispatch)

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	u64 dsq_id = SCX_DSQ_LOCAL;
+	s32 cpu = prev_cpu;
+
+	if (scx_bpf_test_and_clear_cpu_idle(cpu))
+		goto dispatch;
+
+	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+	if (cpu >= 0)
+		goto dispatch;
+
+	dsq_id = SCX_DSQ_GLOBAL;
+	cpu = prev_cpu;
+
+dispatch:
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0);
+	return cpu;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_ops = {
+	.select_cpu		= (void *) select_cpu_dispatch_select_cpu,
+	.name			= "select_cpu_dispatch",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch.c

@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch *skel;
+
+	skel = select_cpu_dispatch__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch *skel = ctx;
+	struct bpf_link *link;
+	pid_t pids[NUM_CHILDREN];
+	int i, status;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			sleep(1);
+			exit(0);
+		}
+	}
+
+	for (i = 0; i < NUM_CHILDREN; i++) {
+		SCX_EQ(waitpid(pids[i], &status, 0), pids[i]);
+		SCX_EQ(status, 0);
+	}
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch *skel = ctx;
+
+	select_cpu_dispatch__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch = {
+	.name = "select_cpu_dispatch",
+	.description = "Test direct dispatching to built-in DSQs from "
+		       "ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch)

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c

@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/* Dispatching to a random DSQ should fail. */
+	scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = {
+	.select_cpu		= (void *) select_cpu_dispatch_bad_dsq_select_cpu,
+	.exit			= (void *) select_cpu_dispatch_bad_dsq_exit,
+	.name			= "select_cpu_dispatch_bad_dsq",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c

@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch_bad_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel;
+
+	skel = select_cpu_dispatch_bad_dsq__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_bad_dsq_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch_bad_dsq *skel = ctx;
+
+	select_cpu_dispatch_bad_dsq__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch_bad_dsq = {
+	.name = "select_cpu_dispatch_bad_dsq",
+	.description = "Verify graceful failure if we direct-dispatch to a "
+		       "bogus DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch_bad_dsq)

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates the behavior of direct dispatching with a default
+ * select_cpu implementation.
+ *
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	/* Dispatching twice in a row is disallowed. */
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = {
+	.select_cpu		= (void *) select_cpu_dispatch_dbl_dsp_select_cpu,
+	.exit			= (void *) select_cpu_dispatch_dbl_dsp_exit,
+	.name			= "select_cpu_dispatch_dbl_dsp",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c

@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2023 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2023 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_dispatch_dbl_dsp.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel;
+
+	skel = select_cpu_dispatch_dbl_dsp__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_dispatch_dbl_dsp_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_dispatch_dbl_dsp *skel = ctx;
+
+	select_cpu_dispatch_dbl_dsp__destroy(skel);
+}
+
+struct scx_test select_cpu_dispatch_dbl_dsp = {
+	.name = "select_cpu_dispatch_dbl_dsp",
+	.description = "Verify graceful failure if we dispatch twice to a "
+		       "DSQ in ops.select_cpu()",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_dispatch_dbl_dsp)

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c

@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A scheduler that validates that enqueue flags are properly stored and
+ * applied at dispatch time when a task is directly dispatched from
+ * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(),
+ * and making the test a very basic vtime scheduler.
+ *
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+volatile bool consumed;
+
+static u64 vtime_now;
+
+#define VTIME_DSQ 0
+
+static inline bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+static inline u64 task_vtime(const struct task_struct *p)
+{
+	u64 vtime = p->scx.dsq_vtime;
+
+	if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL))
+		return vtime_now - SCX_SLICE_DFL;
+	else
+		return vtime;
+}
+
+s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
+		   s32 prev_cpu, u64 wake_flags)
+{
+	s32 cpu;
+
+	cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+	if (cpu >= 0)
+		goto ddsp;
+
+	cpu = prev_cpu;
+	scx_bpf_test_and_clear_cpu_idle(cpu);
+ddsp:
+	scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
+{
+	if (scx_bpf_dsq_move_to_local(VTIME_DSQ, 0))
+		consumed = true;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_running, struct task_struct *p)
+{
+	if (vtime_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_stopping, struct task_struct *p,
+		    bool runnable)
+{
+	u64 delta = scale_by_task_weight_inverse(p, SCX_SLICE_DFL - p->scx.slice);
+
+	scx_bpf_task_set_dsq_vtime(p, p->scx.dsq_vtime + delta);
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_enable, struct task_struct *p)
+{
+	scx_bpf_task_set_dsq_vtime(p, vtime_now);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init)
+{
+	return scx_bpf_create_dsq(VTIME_DSQ, -1);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_vtime_ops = {
+	.select_cpu		= (void *) select_cpu_vtime_select_cpu,
+	.dispatch		= (void *) select_cpu_vtime_dispatch,
+	.running		= (void *) select_cpu_vtime_running,
+	.stopping		= (void *) select_cpu_vtime_stopping,
+	.enable			= (void *) select_cpu_vtime_enable,
+	.init			= (void *) select_cpu_vtime_init,
+	.name			= "select_cpu_vtime",
+	.timeout_ms		= 1000U,
+};

linux-7.2.3/tools/testing/selftests/sched_ext/select_cpu_vtime.c

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "select_cpu_vtime.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct select_cpu_vtime *skel;
+
+	skel = select_cpu_vtime__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct select_cpu_vtime *skel = ctx;
+	struct bpf_link *link;
+
+	SCX_ASSERT(!skel->bss->consumed);
+
+	link = bpf_map__attach_struct_ops(skel->maps.select_cpu_vtime_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	sleep(1);
+
+	SCX_ASSERT(skel->bss->consumed);
+
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct select_cpu_vtime *skel = ctx;
+
+	select_cpu_vtime__destroy(skel);
+}
+
+struct scx_test select_cpu_vtime = {
+	.name = "select_cpu_vtime",
+	.description = "Test doing direct vtime-dispatching from "
+		       "ops.select_cpu(), to a non-built-in DSQ",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&select_cpu_vtime)

linux-7.2.3/tools/testing/selftests/sched_ext/test_example.c

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_test.h"
+
+static bool setup_called = false;
+static bool run_called = false;
+static bool cleanup_called = false;
+
+static int context = 10;
+
+static enum scx_test_status setup(void **ctx)
+{
+	setup_called = true;
+	*ctx = &context;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	int *arg = ctx;
+
+	SCX_ASSERT(setup_called);
+	SCX_ASSERT(!run_called && !cleanup_called);
+	SCX_EQ(*arg, context);
+
+	run_called = true;
+	return SCX_TEST_PASS;
+}
+
+static void cleanup (void *ctx)
+{
+	SCX_BUG_ON(!run_called || cleanup_called, "Wrong callbacks invoked");
+}
+
+struct scx_test example = {
+	.name		= "example",
+	.description	= "Validate the basic function of the test suite itself",
+	.setup		= setup,
+	.run		= run,
+	.cleanup	= cleanup,
+};
+REGISTER_SCX_TEST(&example)

linux-7.2.3/tools/testing/selftests/sched_ext/total_bw.c

@@ -0,0 +1,480 @@
+// 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;
+}
+
+/*
+ * Read a per-CPU dl_server param (runtime or period) from debugfs.
+ * Returns the value in nanoseconds, or -1 on failure.
+ */
+static long read_server_param(const char *server, const char *param, int cpu)
+{
+	char path[128];
+	long value = -1;
+	FILE *fp;
+
+	snprintf(path, sizeof(path),
+		 "/sys/kernel/debug/sched/%s_server/cpu%d/%s",
+		 server, cpu, param);
+	fp = fopen(path, "r");
+	if (!fp)
+		return -1;
+	if (fscanf(fp, "%ld", &value) != 1)
+		value = -1;
+	fclose(fp);
+
+	return value;
+}
+
+/*
+ * Write a per-CPU dl_server param to debugfs. Returns 0 on success.
+ */
+static int write_server_param(const char *server, const char *param,
+			      int cpu, long value)
+{
+	char path[128];
+	FILE *fp;
+	int ret = 0;
+
+	snprintf(path, sizeof(path),
+		 "/sys/kernel/debug/sched/%s_server/cpu%d/%s",
+		 server, cpu, param);
+	fp = fopen(path, "w");
+	if (!fp)
+		return -1;
+	if (fprintf(fp, "%ld", value) < 0)
+		ret = -1;
+	if (fclose(fp) != 0)
+		ret = -1;
+
+	return ret;
+}
+
+static int read_fair_runtime_all(int nr_cpus, long *runtimes)
+{
+	int i;
+
+	for (i = 0; i < nr_cpus; i++) {
+		runtimes[i] = read_server_param("fair", "runtime", i);
+		if (runtimes[i] <= 0)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int write_fair_runtime_all(int nr_cpus, long value)
+{
+	int i;
+
+	for (i = 0; i < nr_cpus; i++) {
+		if (write_server_param("fair", "runtime", i, value) < 0) {
+			SCX_ERR("Failed to write fair_server runtime on CPU %d", i);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Restore per-CPU fair_server runtimes.
+ */
+static int restore_fair_runtime_all(int nr_cpus, const long *runtimes)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < nr_cpus; i++) {
+		if (write_server_param("fair", "runtime", i, runtimes[i]) < 0) {
+			SCX_ERR("Failed to restore fair_server runtime on CPU %d", i);
+			ret = -1;
+		}
+	}
+
+	return ret;
+}
+
+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];
+	long doubled_bw[MAX_CPUS];
+	long original_runtime[MAX_CPUS], doubled_runtime;
+	enum scx_test_status ret;
+	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");
+
+	/*
+	 * Validate auto-register/unregister of dl_server bandwidth reservations.
+	 *
+	 * Doubling fair_server's runtime doubles its bw contribution. With a
+	 * full-mode BPF scheduler (minimal_ops), the kernel should detach
+	 * fair_server and attach ext_server, dropping total_bw back to its
+	 * pre-customization (default ext_server-only) value. On unload, the
+	 * fair_server reservation should come back with its customized runtime
+	 * preserved, so total_bw doubles again.
+	 */
+	if (read_fair_runtime_all(test_ctx->nr_cpus, original_runtime) < 0) {
+		fprintf(stderr, "Skipping attach/detach validation: debugfs not accessible\n");
+		return SCX_TEST_PASS;
+	}
+	doubled_runtime = original_runtime[0] * 2;
+
+	fprintf(stderr,
+		"Setting fair_server runtime to %ld ns on all CPUs (orig %ld)\n",
+		doubled_runtime, original_runtime[0]);
+
+	if (write_fair_runtime_all(test_ctx->nr_cpus, doubled_runtime) < 0) {
+		ret = SCX_TEST_FAIL;
+		goto restore;
+	}
+
+	if (fetch_verify_total_bw(doubled_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values after doubling fair runtime");
+		ret = SCX_TEST_FAIL;
+		goto restore;
+	}
+
+	/*
+	 * After doubling the runtime, fair_server's bw contribution must grow.
+	 * We don't assert exactly 2x, because the kernel's to_ratio() truncates
+	 * the value, so 2 * to_ratio(period, runtime) and
+	 * to_ratio(period, 2 * runtime) can differ.
+	 */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (doubled_bw[i] <= test_ctx->baseline_bw[i]) {
+			SCX_ERR("CPU%d: fair did not increase total_bw (baseline=%ld, doubled=%ld)",
+				i, test_ctx->baseline_bw[i], doubled_bw[i]);
+			ret = SCX_TEST_FAIL;
+			goto restore;
+		}
+	}
+
+	link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler for detach test");
+		ret = SCX_TEST_FAIL;
+		goto restore;
+	}
+
+	if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values with BPF loaded (detach test)");
+		bpf_link__destroy(link);
+		ret = SCX_TEST_FAIL;
+		goto restore;
+	}
+
+	/*
+	 * In full mode the customized fair_server is detached and ext_server is
+	 * attached at its default runtime, total_bw must match baseline.
+	 */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (loaded_bw[i] != test_ctx->baseline_bw[i]) {
+			SCX_ERR("CPU%d: expected bw %ld (fair detached, ext default), got %ld",
+				i, test_ctx->baseline_bw[i], loaded_bw[i]);
+			bpf_link__destroy(link);
+			ret = SCX_TEST_FAIL;
+			goto restore;
+		}
+	}
+
+	bpf_link__destroy(link);
+
+	if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) {
+		SCX_ERR("Failed to get stable values after BPF unload (detach test)");
+		ret = SCX_TEST_FAIL;
+		goto restore;
+	}
+
+	/*
+	 * After unload, fair_server is re-attached with its preserved 2x
+	 * runtime, so total_bw should return to the doubled value.
+	 */
+	for (i = 0; i < test_ctx->nr_cpus; i++) {
+		if (unloaded_bw[i] != doubled_bw[i]) {
+			SCX_ERR("CPU%d: BPF unloaded: expected %ld (fair restored at 2x), got %ld",
+				i, doubled_bw[i], unloaded_bw[i]);
+			ret = SCX_TEST_FAIL;
+			goto restore;
+		}
+	}
+
+	fprintf(stderr,
+		"dl_server attach/detach with customized fair runtime verified\n");
+	ret = SCX_TEST_PASS;
+
+restore:
+	if (restore_fair_runtime_all(test_ctx->nr_cpus, original_runtime) < 0)
+		SCX_ERR("Failed to fully restore per-CPU fair_server runtimes");
+
+	return ret;
+}
+
+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)

linux-7.2.3/tools/testing/selftests/sched_ext/util.c

@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <dvernet@meta.com>
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+/* Returns read len on success, or -errno on failure. */
+static ssize_t read_text(const char *path, char *buf, size_t max_len)
+{
+	ssize_t len;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	len = read(fd, buf, max_len - 1);
+
+	if (len >= 0)
+		buf[len] = 0;
+
+	close(fd);
+	return len < 0 ? -errno : len;
+}
+
+/* Returns written len on success, or -errno on failure. */
+static ssize_t write_text(const char *path, char *buf, ssize_t len)
+{
+	int fd;
+	ssize_t written;
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return -errno;
+
+	written = write(fd, buf, len);
+	close(fd);
+	return written < 0 ? -errno : written;
+}
+
+long file_read_long(const char *path)
+{
+	char buf[128];
+
+
+	if (read_text(path, buf, sizeof(buf)) <= 0)
+		return -1;
+
+	return atol(buf);
+}
+
+int file_write_long(const char *path, long val)
+{
+	char buf[64];
+	int ret;
+
+	ret = sprintf(buf, "%ld", val);
+	if (ret < 0)
+		return ret;
+
+	if (write_text(path, buf, ret) <= 0)
+		return -1;
+
+	return 0;
+}

linux-7.2.3/tools/testing/selftests/sched_ext/util.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2024 David Vernet <void@manifault.com>
+ */
+
+#ifndef __SCX_TEST_UTIL_H__
+#define __SCX_TEST_UTIL_H__
+
+long file_read_long(const char *path);
+int file_write_long(const char *path, long val);
+
+#endif // __SCX_TEST_UTIL_H__