add sched

README.md

@@ -87,6 +87,9 @@ Other:
 - [Using user ring buffer to send information to the kernel](src/35-user-ringbuf/README.md)
 - [Userspace eBPF Runtimes: Overview and Applications](src/36-userspace-ebpf/README.md)
 - [Compile Once, Run Everywhere for userspace trace with eBPF and BTF](src/38-btf-uprobe/README.md)
+- [Extending eBPF Beyond Its Limits: Custom kfuncs in Kernel Modules](src/43-kfuncs/README.md)
+
+
 
 Continuously updating...
 

src/44-scx-simple/.gitignore

@@ -0,0 +1 @@
+scx_simple

src/44-scx-simple/Makefile

@@ -0,0 +1,144 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+OUTPUT := .output
+CLANG ?= clang
+LIBBPF_SRC := $(abspath ../third_party/libbpf/src)
+BPFTOOL_SRC := $(abspath ../third_party/bpftool/src)
+LIBBPF_OBJ := $(abspath $(OUTPUT)/libbpf.a)
+BPFTOOL_OUTPUT ?= $(abspath $(OUTPUT)/bpftool)
+BPFTOOL ?= $(BPFTOOL_OUTPUT)/bootstrap/bpftool
+LIBBLAZESYM_SRC := $(abspath ../third_party/blazesym/)
+LIBBLAZESYM_OBJ := $(abspath $(OUTPUT)/libblazesym.a)
+LIBBLAZESYM_HEADER := $(abspath $(OUTPUT)/blazesym.h)
+ARCH ?= $(shell uname -m | sed 's/x86_64/x86/' \
+			 | sed 's/arm.*/arm/' \
+			 | sed 's/aarch64/arm64/' \
+			 | sed 's/ppc64le/powerpc/' \
+			 | sed 's/mips.*/mips/' \
+			 | sed 's/riscv64/riscv/' \
+			 | sed 's/loongarch64/loongarch/')
+VMLINUX := ../third_party/vmlinux/$(ARCH)/vmlinux.h
+# Use our own libbpf API headers and Linux UAPI headers distributed with
+# libbpf to avoid dependency on system-wide headers, which could be missing or
+# outdated
+INCLUDES := -I$(OUTPUT) -I../third_party/libbpf/include/uapi -Iinclude/ -I$(dir $(VMLINUX))
+CFLAGS := -g -Wall 
+ALL_LDFLAGS := $(LDFLAGS) $(EXTRA_LDFLAGS)
+
+APPS = scx_simple
+
+CARGO ?= $(shell which cargo)
+ifeq ($(strip $(CARGO)),)
+BZS_APPS :=
+else
+BZS_APPS := 
+APPS += $(BZS_APPS)
+# Required by libblazesym
+ALL_LDFLAGS += -lrt -ldl -lpthread -lm
+endif
+
+# Get Clang's default includes on this system. We'll explicitly add these dirs
+# to the includes list when compiling with `-target bpf` because otherwise some
+# architecture-specific dirs will be "missing" on some architectures/distros -
+# headers such as asm/types.h, asm/byteorder.h, asm/socket.h, asm/sockios.h,
+# sys/cdefs.h etc. might be missing.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+CLANG_BPF_SYS_INCLUDES ?= $(shell $(CLANG) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+
+ifeq ($(V),1)
+	Q =
+	msg =
+else
+	Q = @
+	msg = @printf '  %-8s %s%s\n'					\
+		      "$(1)"						\
+		      "$(patsubst $(abspath $(OUTPUT))/%,%,$(2))"	\
+		      "$(if $(3), $(3))";
+	MAKEFLAGS += --no-print-directory
+endif
+
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+$(call allow-override,CC,$(CROSS_COMPILE)cc)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
+.PHONY: all
+all: $(APPS)
+
+.PHONY: clean
+clean:
+	$(call msg,CLEAN)
+	$(Q)rm -rf $(OUTPUT) $(APPS)
+
+$(OUTPUT) $(OUTPUT)/libbpf $(BPFTOOL_OUTPUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $@
+
+# Build libbpf
+$(LIBBPF_OBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf
+	$(call msg,LIB,$@)
+	$(Q)$(MAKE) -C $(LIBBPF_SRC) BUILD_STATIC_ONLY=1		      \
+		    OBJDIR=$(dir $@)/libbpf DESTDIR=$(dir $@)		      \
+		    INCLUDEDIR= LIBDIR= UAPIDIR=			      \
+		    install
+
+# Build bpftool
+$(BPFTOOL): | $(BPFTOOL_OUTPUT)
+	$(call msg,BPFTOOL,$@)
+	$(Q)$(MAKE) ARCH= CROSS_COMPILE= OUTPUT=$(BPFTOOL_OUTPUT)/ -C $(BPFTOOL_SRC) bootstrap
+
+
+$(LIBBLAZESYM_SRC)/target/release/libblazesym.a::
+	$(Q)cd $(LIBBLAZESYM_SRC) && $(CARGO) build --features=cheader,dont-generate-test-files --release
+
+$(LIBBLAZESYM_OBJ): $(LIBBLAZESYM_SRC)/target/release/libblazesym.a | $(OUTPUT)
+	$(call msg,LIB, $@)
+	$(Q)cp $(LIBBLAZESYM_SRC)/target/release/libblazesym.a $@
+
+$(LIBBLAZESYM_HEADER): $(LIBBLAZESYM_SRC)/target/release/libblazesym.a | $(OUTPUT)
+	$(call msg,LIB,$@)
+	$(Q)cp $(LIBBLAZESYM_SRC)/target/release/blazesym.h $@
+
+# Build BPF code
+$(OUTPUT)/%.bpf.o: %.bpf.c $(LIBBPF_OBJ) $(wildcard %.h) $(VMLINUX) | $(OUTPUT) $(BPFTOOL)
+	$(call msg,BPF,$@)
+	$(Q)$(CLANG) -mlittle-endian  -g -O2  -mcpu=v3 -target bpf -D__TARGET_ARCH_$(ARCH)		      \
+		     $(INCLUDES) $(CLANG_BPF_SYS_INCLUDES)		      \
+		     -c $(filter %.c,$^) -o $(patsubst %.bpf.o,%.tmp.bpf.o,$@)
+	$(Q)$(BPFTOOL) gen object $@ $(patsubst %.bpf.o,%.tmp.bpf.o,$@)
+
+# Generate BPF skeletons
+$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(OUTPUT) $(BPFTOOL)
+	$(Q)$(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)
+	$(call msg,GEN-SKEL,$@)
+	$(Q)$(BPFTOOL)  gen skeleton $< name $(APPS) > $@
+
+# Build user-space code
+$(patsubst %,$(OUTPUT)/%.o,$(APPS)): %.o: %.skel.h
+
+$(OUTPUT)/%.o: %.c $(wildcard %.h) | $(OUTPUT)
+	$(call msg,CC,$@)
+	$(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@
+
+$(patsubst %,$(OUTPUT)/%.o,$(BZS_APPS)): $(LIBBLAZESYM_HEADER)
+
+$(BZS_APPS): $(LIBBLAZESYM_OBJ)
+
+# Build application binary
+$(APPS): %: $(OUTPUT)/%.o $(LIBBPF_OBJ) | $(OUTPUT)
+	$(call msg,BINARY,$@)
+	$(Q)$(CC) $(CFLAGS) $^ $(ALL_LDFLAGS) -lelf -lz -o $@
+
+# delete failed targets
+.DELETE_ON_ERROR:
+
+# keep intermediate (.skel.h, .bpf.o, etc) targets
+.SECONDARY:

src/44-scx-simple/README_en.md

@@ -0,0 +1,425 @@
+# eBPF Tutorial by Example: Introduction to the BPF Scheduler
+
+Welcome to our deep dive into the world of eBPF with a focus on the BPF scheduler! If you're looking to extend your eBPF knowledge beyond the basics, you're in the right place. In this tutorial, we'll explore the **scx_simple scheduler**, a minimal example of the sched_ext scheduler class introduced in Linux kernel version 6.12. We'll walk you through its architecture, how it leverages BPF programs to define scheduling behavior, and guide you through compiling and running the example. By the end, you'll have a solid understanding of how to create and manage advanced scheduling policies using eBPF.
+
+## Understanding the Extensible BPF Scheduler
+
+At the heart of this tutorial is the **sched_ext** scheduler class. Unlike traditional schedulers, sched_ext allows its behavior to be defined dynamically through a set of BPF programs, making it highly flexible and customizable. This means you can implement any scheduling algorithm on top of sched_ext, tailored to your specific needs.
+
+### Key Features of sched_ext
+
+- **Flexible Scheduling Algorithms:** Implement any scheduling policy by writing BPF programs.
+- **Dynamic CPU Grouping:** The BPF scheduler can group CPUs as needed, without tying tasks to specific CPUs upon wakeup.
+- **Runtime Control:** Enable or disable the BPF scheduler on-the-fly without rebooting.
+- **System Integrity:** Even if the BPF scheduler encounters errors, the system gracefully reverts to the default scheduling behavior.
+- **Debugging Support:** Comprehensive debug information is available through the `sched_ext_dump` tracepoint and SysRq key sequences.
+
+With these features, sched_ext provides a robust foundation for experimenting with and deploying advanced scheduling strategies.
+
+## Introducing scx_simple: A Minimal sched_ext Scheduler
+
+The **scx_simple** scheduler is a straightforward example of a sched_ext scheduler. It's designed to be easy to understand and serves as a foundation for more complex scheduling policies. scx_simple can operate in two modes:
+
+1. **Global Weighted Virtual Time (vtime) Mode:** Prioritizes tasks based on their virtual time, allowing for fair scheduling across different workloads.
+2. **FIFO (First-In-First-Out) Mode:** Simple queue-based scheduling where tasks are executed in the order they arrive.
+
+### Use Case and Suitability
+
+scx_simple is particularly effective on single-socket CPUs with a uniform L3 cache topology. While the global FIFO mode can handle many workloads efficiently, it's essential to note that saturating threads might overshadow less active ones. Therefore, scx_simple is best suited for environments where a straightforward scheduling policy meets the performance and fairness requirements.
+
+### Production Readiness
+
+While scx_simple is minimalistic, it can be deployed in production settings under the right conditions:
+
+- **Hardware Constraints:** Best suited for systems with single-socket CPUs and uniform cache architectures.
+- **Workload Characteristics:** Ideal for workloads that don't require intricate scheduling policies and can benefit from simple FIFO or weighted vtime scheduling.
+
+## Diving into the Code: Kernel and User-Space Analysis
+
+Let's explore how scx_simple is implemented both in the kernel and user-space. We'll start by presenting the complete code snippets and then break down their functionalities.
+
+### Kernel-Side Implementation
+
+```c
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile bool fifo_sched;
+
+static u64 vtime_now;
+UEI_DEFINE(uei);
+
+/*
+ * Built-in DSQs such as SCX_DSQ_GLOBAL cannot be used as priority queues
+ * (meaning, cannot be dispatched to with scx_bpf_dispatch_vtime()). We
+ * therefore create a separate DSQ with ID 0 that we dispatch to and consume
+ * from. If scx_simple only supported global FIFO scheduling, then we could
+ * just use SCX_DSQ_GLOBAL.
+ */
+#define SHARED_DSQ 0
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+	__uint(max_entries, 2);			/* [local, global] */
+} stats SEC(".maps");
+
+static void stat_inc(u32 idx)
+{
+	u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx);
+	if (cnt_p)
+		(*cnt_p)++;
+}
+
+static inline bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	bool is_idle = false;
+	s32 cpu;
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle);
+	if (is_idle) {
+		stat_inc(0);	/* count local queueing */
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+	}
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	stat_inc(1);	/* count global queueing */
+
+	if (fifo_sched) {
+		scx_bpf_dispatch(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags);
+	} else {
+		u64 vtime = p->scx.dsq_vtime;
+
+		/*
+		 * Limit the amount of budget that an idling task can accumulate
+		 * to one slice.
+		 */
+		if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL))
+			vtime = vtime_now - SCX_SLICE_DFL;
+
+		scx_bpf_dispatch_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime,
+				       enq_flags);
+	}
+}
+
+void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_consume(SHARED_DSQ);
+}
+
+void BPF_STRUCT_OPS(simple_running, struct task_struct *p)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Global vtime always progresses forward as tasks start executing. The
+	 * test and update can be performed concurrently from multiple CPUs and
+	 * thus racy. Any error should be contained and temporary. Let's just
+	 * live with it.
+	 */
+	if (vtime_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(simple_stopping, struct task_struct *p, bool runnable)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Scale the execution time by the inverse of the weight and charge.
+	 *
+	 * Note that the default yield implementation yields by setting
+	 * @p->scx.slice to zero and the following would treat the yielding task
+	 * as if it has consumed all its slice. If this penalizes yielding tasks
+	 * too much, determine the execution time by taking explicit timestamps
+	 * instead of depending on @p->scx.slice.
+	 */
+	p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+}
+
+void BPF_STRUCT_OPS(simple_enable, struct task_struct *p)
+{
+	p->scx.dsq_vtime = vtime_now;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init)
+{
+	return scx_bpf_create_dsq(SHARED_DSQ, -1);
+}
+
+void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(simple_ops,
+	       .select_cpu		= (void *)simple_select_cpu,
+	       .enqueue			= (void *)simple_enqueue,
+	       .dispatch		= (void *)simple_dispatch,
+	       .running			= (void *)simple_running,
+	       .stopping		= (void *)simple_stopping,
+	       .enable			= (void *)simple_enable,
+	       .init			= (void *)simple_init,
+	       .exit			= (void *)simple_exit,
+	       .name			= "simple");
+```
+
+#### Kernel-Side Breakdown
+
+The kernel-side implementation of scx_simple defines how tasks are selected, enqueued, dispatched, and managed. Here's a high-level overview:
+
+1. **Initialization and Licensing:**
+   - The scheduler is licensed under GPL.
+   - A global variable `fifo_sched` determines the scheduling mode (FIFO or weighted vtime).
+
+2. **Dispatch Queue (DSQ) Management:**
+   - A shared DSQ (`SHARED_DSQ`) with ID 0 is created to handle task dispatching.
+   - A `stats` map tracks the number of tasks queued locally and globally.
+
+3. **CPU Selection (`simple_select_cpu`):**
+   - Selects the CPU for a waking task.
+   - If the selected CPU is idle, the task is immediately dispatched to the local DSQ.
+
+4. **Task Enqueueing (`simple_enqueue`):**
+   - Depending on the `fifo_sched` flag, tasks are either dispatched to the shared DSQ in FIFO mode or to a priority queue based on virtual time.
+   - Virtual time (`vtime`) ensures fair scheduling by accounting for task execution time and weight.
+
+5. **Task Dispatching (`simple_dispatch`):**
+   - Consumes tasks from the shared DSQ and assigns them to CPUs.
+
+6. **Running and Stopping Tasks (`simple_running` & `simple_stopping`):**
+   - Manages the progression of virtual time for tasks, ensuring that scheduling decisions remain fair and balanced.
+
+7. **Enabling and Exiting:**
+   - Handles the enabling of the scheduler and records exit information for debugging.
+
+This modular structure allows scx_simple to be both simple and effective, providing a clear example of how to implement custom scheduling policies using eBPF.
+
+### User-Space Implementation
+
+```c
+static void read_stats(struct scx_simple *skel, __u64 *stats)
+{
+	int nr_cpus = libbpf_num_possible_cpus();
+	__u64 cnts[2][nr_cpus];
+	__u32 idx;
+
+	memset(stats, 0, sizeof(stats[0]) * 2);
+
+	for (idx = 0; idx < 2; idx++) {
+		int ret, cpu;
+
+		ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats),
+					  &idx, cnts[idx]);
+		if (ret < 0)
+			continue;
+		for (cpu = 0; cpu < nr_cpus; cpu++)
+			stats[idx] += cnts[idx][cpu];
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct scx_simple *skel;
+	struct bpf_link *link;
+	__u32 opt;
+	__u64 ecode;
+
+	libbpf_set_print(libbpf_print_fn);
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+restart:
+	skel = SCX_OPS_OPEN(simple_ops, scx_simple);
+
+	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+		switch (opt) {
+		case 'f':
+			skel->rodata->fifo_sched = true;
+			break;
+		case 'v':
+			verbose = true;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	SCX_OPS_LOAD(skel, simple_ops, scx_simple, uei);
+	link = SCX_OPS_ATTACH(skel, simple_ops, scx_simple);
+
+	while (!exit_req && !UEI_EXITED(skel, uei)) {
+		__u64 stats[2];
+
+		read_stats(skel, stats);
+		printf("local=%llu global=%llu\n", stats[0], stats[1]);
+		fflush(stdout);
+		sleep(1);
+	}
+
+	bpf_link__destroy(link);
+	ecode = UEI_REPORT(skel, uei);
+	scx_simple__destroy(skel);
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
+	return 0;
+}
+```
+
+#### User-Space Breakdown
+
+The user-space component is responsible for interacting with the BPF scheduler, managing its lifecycle, and monitoring its performance. Here's a snapshot of its responsibilities:
+
+1. **Statistics Collection (`read_stats`):**
+   - Reads the number of tasks queued locally and globally from the BPF maps.
+   - Aggregates statistics across all CPUs for reporting.
+
+2. **Main Function Workflow:**
+   - **Initialization:** Sets up libbpf, handles signal interrupts, and opens the scx_simple BPF skeleton.
+   - **Argument Parsing:** Processes command-line options to toggle FIFO scheduling and verbosity.
+   - **Loading and Attaching:** Loads the BPF program and attaches it to the scheduler.
+   - **Monitoring Loop:** Continuously reads and prints scheduling statistics every second.
+   - **Cleanup:** Destroys BPF links and handles potential restarts based on exit codes.
+
+This user-space program provides a straightforward interface to monitor and control the scx_simple scheduler, making it easier to understand its behavior in real-time.
+
+## Deep Dive into Key Concepts
+
+To fully grasp how scx_simple operates, let's explore some of the underlying concepts and mechanisms:
+
+### Dispatch Queues (DSQs)
+
+DSQs are central to sched_ext's operation, acting as buffers where tasks are queued before being dispatched to CPUs. They can function as either FIFO queues or priority queues based on virtual time.
+
+- **Local DSQs (`SCX_DSQ_LOCAL`):** Each CPU has its own local DSQ, ensuring that tasks can be dispatched and consumed efficiently without contention.
+- **Global DSQ (`SCX_DSQ_GLOBAL`):** A shared queue where tasks from all CPUs can be queued, providing a fallback when local queues are empty.
+- **Custom DSQs:** Developers can create additional DSQs using `scx_bpf_create_dsq()` for more specialized scheduling needs.
+
+### Virtual Time (vtime)
+
+Virtual time is a mechanism to ensure fairness in scheduling by tracking how much time a task has consumed relative to its weight. In scx_simple's weighted vtime mode, tasks with higher weights consume virtual time more slowly, allowing lower-weighted tasks to run more frequently.
+
+### Scheduling Cycle
+
+Understanding the scheduling cycle is crucial for modifying or extending scx_simple:
+
+1. **Task Wakeup:**
+   - `ops.select_cpu()` is invoked to select an optimal CPU for the waking task.
+   - If the selected CPU is idle, the task is dispatched immediately to the local DSQ.
+
+2. **Task Enqueueing:**
+   - `ops.enqueue()` decides whether to dispatch the task to the global DSQ, a local DSQ, or a custom DSQ based on the scheduling mode.
+
+3. **Task Dispatching:**
+   - When a CPU is ready to schedule, it first checks its local DSQ, then the global DSQ, and finally invokes `ops.dispatch()` if needed.
+
+4. **Task Execution:**
+   - The CPU executes the selected task, updating its virtual time and ensuring fair scheduling.
+
+This cycle ensures that tasks are scheduled efficiently while maintaining fairness and responsiveness.
+
+## Compiling and Running scx_simple
+
+Getting scx_simple up and running involves setting up the necessary toolchain and configuring the kernel appropriately. Here's how you can compile and execute the example scheduler.
+
+### Toolchain Dependencies
+
+Before compiling scx_simple, ensure you have the following tools installed:
+
+1. **clang >= 16.0.0**
+   - Required for compiling BPF programs. While GCC is working on BPF support, it lacks essential features like BTF type tags necessary for certain functionalities.
+
+2. **pahole >= 1.25**
+   - Used to generate BTF from DWARF, which is crucial for type information in BPF programs.
+
+3. **rust >= 1.70.0**
+   - If you're working with Rust-based schedulers, ensure you have the appropriate Rust toolchain version.
+
+Additionally, tools like `make` are required for building the examples.
+
+### Kernel Configuration
+
+To enable and use sched_ext, ensure the following kernel configuration options are set:
+
+```plaintext
+CONFIG_BPF=y
+CONFIG_SCHED_CLASS_EXT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_PAHOLE_HAS_SPLIT_BTF=y
+CONFIG_PAHOLE_HAS_BTF_TAG=y
+```
+
+These configurations enable the necessary features for BPF scheduling and ensure that sched_ext operates correctly.
+
+### Building scx_simple
+
+Navigate to the kernel's `tools/sched_ext/` directory and run:
+
+```bash
+make
+```
+
+This command compiles the scx_simple scheduler along with its dependencies.
+
+### Running scx_simple
+
+Once compiled, you can execute the user-space program to load and monitor the scheduler:
+
+```bash
+./scx_simple -f
+```
+
+The `-f` flag enables FIFO scheduling mode. You can also use `-v` for verbose output or `-h` for help.
+
+As the program runs, it will display the number of tasks queued locally and globally every second:
+
+```plaintext
+local=123 global=456
+local=124 global=457
+...
+```
+
+### Switching Between sched_ext and CFS
+
+sched_ext operates alongside the default Completely Fair Scheduler (CFS). You can switch between sched_ext and CFS dynamically:
+
+- **Enable sched_ext:** Load the BPF scheduler using scx_simple.
+- **Disable sched_ext:** Terminate the scx_simple program, reverting all tasks back to CFS.
+
+Additionally, using SysRq key sequences like `SysRq-S` can help manage the scheduler's state and trigger debug dumps with `SysRq-D`.
+
+## Summary and Next Steps
+
+In this tutorial, we've introduced the **sched_ext** scheduler class and walked through a minimal example, **scx_simple**, demonstrating how to define custom scheduling behaviors using eBPF programs. We've covered the architecture, key concepts like DSQs and virtual time, and provided step-by-step instructions for compiling and running the scheduler.
+
+By mastering scx_simple, you're well-equipped to design and implement more sophisticated scheduling policies tailored to your specific requirements. Whether you're optimizing for performance, fairness, or specific workload characteristics, sched_ext and eBPF offer the flexibility and power to achieve your goals.
+
+> Ready to take your eBPF skills to the next level? Dive deeper into our tutorials and explore more examples by visiting our [tutorial repository](https://github.com/eunomia-bpf/bpf-developer-tutorial) or our [website](https://eunomia.dev/tutorials/).
+
+## References
+
+- **sched_ext Repository:** [https://github.com/sched-ext/scx](https://github.com/sched-ext/scx)
+- **Linux Kernel Documentation:** [Scheduler Ext Documentation](https://www.kernel.org/doc/html/next/scheduler/sched-ext.html)
+- **Kernel Source Tree:** [Linux Kernel sched_ext Tools](https://github.com/torvalds/linux/tree/master/tools/sched_ext)
+- **eBPF Official Documentation:** [https://ebpf.io/docs/](https://ebpf.io/docs/)
+- **libbpf Documentation:** [https://github.com/libbpf/libbpf](https://github.com/libbpf/libbpf)
+
+Feel free to explore these resources to expand your understanding and continue your journey into advanced eBPF programming!

src/44-scx-simple/include/bpf-compat/gnu/stubs.h

@@ -0,0 +1,11 @@
+/*
+ * Dummy gnu/stubs.h. clang can end up including /usr/include/gnu/stubs.h when
+ * compiling BPF files although its content doesn't play any role. The file in
+ * turn includes stubs-64.h or stubs-32.h depending on whether __x86_64__ is
+ * defined. When compiling a BPF source, __x86_64__ isn't set and thus
+ * stubs-32.h is selected. However, the file is not there if the system doesn't
+ * have 32bit glibc devel package installed leading to a build failure.
+ *
+ * The problem is worked around by making this file available in the include
+ * search paths before the system one when building BPF.
+ */

src/44-scx-simple/include/scx/common.bpf.h

@@ -0,0 +1,427 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#ifndef __SCX_COMMON_BPF_H
+#define __SCX_COMMON_BPF_H
+
+#ifdef LSP
+#define __bpf__
+#include "../vmlinux/vmlinux.h"
+#else
+#include "vmlinux.h"
+#endif
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <asm-generic/errno.h>
+#include "user_exit_info.h"
+
+#define PF_WQ_WORKER			0x00000020	/* I'm a workqueue worker */
+#define PF_KTHREAD			0x00200000	/* I am a kernel thread */
+#define PF_EXITING			0x00000004
+#define CLOCK_MONOTONIC			1
+
+/*
+ * Earlier versions of clang/pahole lost upper 32bits in 64bit enums which can
+ * lead to really confusing misbehaviors. Let's trigger a build failure.
+ */
+static inline void ___vmlinux_h_sanity_check___(void)
+{
+	_Static_assert(SCX_DSQ_FLAG_BUILTIN,
+		       "bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole");
+}
+
+s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym;
+s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym;
+void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym;
+void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym;
+u32 scx_bpf_dispatch_nr_slots(void) __ksym;
+void scx_bpf_dispatch_cancel(void) __ksym;
+bool scx_bpf_consume(u64 dsq_id) __ksym;
+void scx_bpf_dispatch_from_dsq_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym;
+void scx_bpf_dispatch_from_dsq_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym;
+bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
+bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
+u32 scx_bpf_reenqueue_local(void) __ksym;
+void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym;
+s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym;
+void scx_bpf_destroy_dsq(u64 dsq_id) __ksym;
+int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, u64 flags) __ksym __weak;
+struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak;
+void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak;
+void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak;
+void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym;
+void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym __weak;
+u32 scx_bpf_cpuperf_cap(s32 cpu) __ksym __weak;
+u32 scx_bpf_cpuperf_cur(s32 cpu) __ksym __weak;
+void scx_bpf_cpuperf_set(s32 cpu, u32 perf) __ksym __weak;
+u32 scx_bpf_nr_cpu_ids(void) __ksym __weak;
+const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym __weak;
+const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym __weak;
+void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym __weak;
+const struct cpumask *scx_bpf_get_idle_cpumask(void) __ksym;
+const struct cpumask *scx_bpf_get_idle_smtmask(void) __ksym;
+void scx_bpf_put_idle_cpumask(const struct cpumask *cpumask) __ksym;
+bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym;
+s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
+s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
+bool scx_bpf_task_running(const struct task_struct *p) __ksym;
+s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
+struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
+struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym;
+
+/*
+ * Use the following as @it__iter when calling
+ * scx_bpf_dispatch[_vtime]_from_dsq() from within bpf_for_each() loops.
+ */
+#define BPF_FOR_EACH_ITER	(&___it)
+
+static inline __attribute__((format(printf, 1, 2)))
+void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {}
+
+/*
+ * Helper macro for initializing the fmt and variadic argument inputs to both
+ * bstr exit kfuncs. Callers to this function should use ___fmt and ___param to
+ * refer to the initialized list of inputs to the bstr kfunc.
+ */
+#define scx_bpf_bstr_preamble(fmt, args...)					\
+	static char ___fmt[] = fmt;						\
+	/*									\
+	 * Note that __param[] must have at least one				\
+	 * element to keep the verifier happy.					\
+	 */									\
+	unsigned long long ___param[___bpf_narg(args) ?: 1] = {};		\
+										\
+	_Pragma("GCC diagnostic push")						\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")			\
+	___bpf_fill(___param, args);						\
+	_Pragma("GCC diagnostic pop")						\
+
+/*
+ * scx_bpf_exit() wraps the scx_bpf_exit_bstr() kfunc with variadic arguments
+ * instead of an array of u64. Using this macro will cause the scheduler to
+ * exit cleanly with the specified exit code being passed to user space.
+ */
+#define scx_bpf_exit(code, fmt, args...)					\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_exit_bstr(code, ___fmt, ___param, sizeof(___param));		\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+/*
+ * scx_bpf_error() wraps the scx_bpf_error_bstr() kfunc with variadic arguments
+ * instead of an array of u64. Invoking this macro will cause the scheduler to
+ * exit in an erroneous state, with diagnostic information being passed to the
+ * user.
+ */
+#define scx_bpf_error(fmt, args...)						\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_error_bstr(___fmt, ___param, sizeof(___param));			\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+/*
+ * scx_bpf_dump() wraps the scx_bpf_dump_bstr() kfunc with variadic arguments
+ * instead of an array of u64. To be used from ops.dump() and friends.
+ */
+#define scx_bpf_dump(fmt, args...)						\
+({										\
+	scx_bpf_bstr_preamble(fmt, args)					\
+	scx_bpf_dump_bstr(___fmt, ___param, sizeof(___param));			\
+	___scx_bpf_bstr_format_checker(fmt, ##args);				\
+})
+
+#define BPF_STRUCT_OPS(name, args...)						\
+SEC("struct_ops/"#name)								\
+BPF_PROG(name, ##args)
+
+#define BPF_STRUCT_OPS_SLEEPABLE(name, args...)					\
+SEC("struct_ops.s/"#name)							\
+BPF_PROG(name, ##args)
+
+/**
+ * RESIZABLE_ARRAY - Generates annotations for an array that may be resized
+ * @elfsec: the data section of the BPF program in which to place the array
+ * @arr: the name of the array
+ *
+ * libbpf has an API for setting map value sizes. Since data sections (i.e.
+ * bss, data, rodata) themselves are maps, a data section can be resized. If
+ * a data section has an array as its last element, the BTF info for that
+ * array will be adjusted so that length of the array is extended to meet the
+ * new length of the data section. This macro annotates an array to have an
+ * element count of one with the assumption that this array can be resized
+ * within the userspace program. It also annotates the section specifier so
+ * this array exists in a custom sub data section which can be resized
+ * independently.
+ *
+ * See RESIZE_ARRAY() for the userspace convenience macro for resizing an
+ * array declared with RESIZABLE_ARRAY().
+ */
+#define RESIZABLE_ARRAY(elfsec, arr) arr[1] SEC("."#elfsec"."#arr)
+
+/**
+ * MEMBER_VPTR - Obtain the verified pointer to a struct or array member
+ * @base: struct or array to index
+ * @member: dereferenced member (e.g. .field, [idx0][idx1], .field[idx0] ...)
+ *
+ * The verifier often gets confused by the instruction sequence the compiler
+ * generates for indexing struct fields or arrays. This macro forces the
+ * compiler to generate a code sequence which first calculates the byte offset,
+ * checks it against the struct or array size and add that byte offset to
+ * generate the pointer to the member to help the verifier.
+ *
+ * Ideally, we want to abort if the calculated offset is out-of-bounds. However,
+ * BPF currently doesn't support abort, so evaluate to %NULL instead. The caller
+ * must check for %NULL and take appropriate action to appease the verifier. To
+ * avoid confusing the verifier, it's best to check for %NULL and dereference
+ * immediately.
+ *
+ *	vptr = MEMBER_VPTR(my_array, [i][j]);
+ *	if (!vptr)
+ *		return error;
+ *	*vptr = new_value;
+ *
+ * sizeof(@base) should encompass the memory area to be accessed and thus can't
+ * be a pointer to the area. Use `MEMBER_VPTR(*ptr, .member)` instead of
+ * `MEMBER_VPTR(ptr, ->member)`.
+ */
+#define MEMBER_VPTR(base, member) (typeof((base) member) *)			\
+({										\
+	u64 __base = (u64)&(base);						\
+	u64 __addr = (u64)&((base) member) - __base;				\
+	_Static_assert(sizeof(base) >= sizeof((base) member),			\
+		       "@base is smaller than @member, is @base a pointer?");	\
+	asm volatile (								\
+		"if %0 <= %[max] goto +2\n"					\
+		"%0 = 0\n"							\
+		"goto +1\n"							\
+		"%0 += %1\n"							\
+		: "+r"(__addr)							\
+		: "r"(__base),							\
+		  [max]"i"(sizeof(base) - sizeof((base) member)));		\
+	__addr;									\
+})
+
+/**
+ * ARRAY_ELEM_PTR - Obtain the verified pointer to an array element
+ * @arr: array to index into
+ * @i: array index
+ * @n: number of elements in array
+ *
+ * Similar to MEMBER_VPTR() but is intended for use with arrays where the
+ * element count needs to be explicit.
+ * It can be used in cases where a global array is defined with an initial
+ * size but is intended to be be resized before loading the BPF program.
+ * Without this version of the macro, MEMBER_VPTR() will use the compile time
+ * size of the array to compute the max, which will result in rejection by
+ * the verifier.
+ */
+#define ARRAY_ELEM_PTR(arr, i, n) (typeof(arr[i]) *)				\
+({										\
+	u64 __base = (u64)arr;							\
+	u64 __addr = (u64)&(arr[i]) - __base;					\
+	asm volatile (								\
+		"if %0 <= %[max] goto +2\n"					\
+		"%0 = 0\n"							\
+		"goto +1\n"							\
+		"%0 += %1\n"							\
+		: "+r"(__addr)							\
+		: "r"(__base),							\
+		  [max]"r"(sizeof(arr[0]) * ((n) - 1)));			\
+	__addr;									\
+})
+
+
+/*
+ * BPF declarations and helpers
+ */
+
+/* list and rbtree */
+#define __contains(name, node) __attribute__((btf_decl_tag("contains:" #name ":" #node)))
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
+void bpf_obj_drop_impl(void *kptr, void *meta) __ksym;
+
+#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL))
+#define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL)
+
+void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym;
+struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym;
+struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
+				      struct bpf_rb_node *node) __ksym;
+int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node,
+			bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b),
+			void *meta, __u64 off) __ksym;
+#define bpf_rbtree_add(head, node, less) bpf_rbtree_add_impl(head, node, less, NULL, 0)
+
+struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym;
+
+void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym;
+#define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL)
+
+/* task */
+struct task_struct *bpf_task_from_pid(s32 pid) __ksym;
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* cgroup */
+struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+
+/* css iteration */
+struct bpf_iter_css;
+struct cgroup_subsys_state;
+extern int bpf_iter_css_new(struct bpf_iter_css *it,
+			    struct cgroup_subsys_state *start,
+			    unsigned int flags) __weak __ksym;
+extern struct cgroup_subsys_state *
+bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym;
+extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
+
+/* cpumask */
+struct bpf_cpumask *bpf_cpumask_create(void) __ksym;
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym;
+u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym;
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym;
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym;
+bool bpf_cpumask_and(struct bpf_cpumask *dst, const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+void bpf_cpumask_or(struct bpf_cpumask *dst, const struct cpumask *src1,
+		    const struct cpumask *src2) __ksym;
+void bpf_cpumask_xor(struct bpf_cpumask *dst, const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym;
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym;
+bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym;
+bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym;
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym;
+u32 bpf_cpumask_any_distribute(const struct cpumask *cpumask) __ksym;
+u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
+				   const struct cpumask *src2) __ksym;
+u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym;
+
+/*
+ * Access a cpumask in read-only mode (typically to check bits).
+ */
+const struct cpumask *cast_mask(struct bpf_cpumask *mask)
+{
+	return (const struct cpumask *)mask;
+}
+
+/* rcu */
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+
+/*
+ * Other helpers
+ */
+
+/* useful compiler attributes */
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#define __maybe_unused __attribute__((__unused__))
+
+/*
+ * READ/WRITE_ONCE() are from kernel (include/asm-generic/rwonce.h). They
+ * prevent compiler from caching, redoing or reordering reads or writes.
+ */
+typedef __u8  __attribute__((__may_alias__))  __u8_alias_t;
+typedef __u16 __attribute__((__may_alias__)) __u16_alias_t;
+typedef __u32 __attribute__((__may_alias__)) __u32_alias_t;
+typedef __u64 __attribute__((__may_alias__)) __u64_alias_t;
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8_alias_t  *) res = *(volatile __u8_alias_t  *) p; break;
+	case 2: *(__u16_alias_t *) res = *(volatile __u16_alias_t *) p; break;
+	case 4: *(__u32_alias_t *) res = *(volatile __u32_alias_t *) p; break;
+	case 8: *(__u64_alias_t *) res = *(volatile __u64_alias_t *) p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile  __u8_alias_t *) p = *(__u8_alias_t  *) res; break;
+	case 2: *(volatile __u16_alias_t *) p = *(__u16_alias_t *) res; break;
+	case 4: *(volatile __u32_alias_t *) p = *(__u32_alias_t *) res; break;
+	case 8: *(volatile __u64_alias_t *) p = *(__u64_alias_t *) res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+#define READ_ONCE(x)					\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__c = { 0 } };			\
+	__read_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+#define WRITE_ONCE(x, val)				\
+({							\
+	union { typeof(x) __val; char __c[1]; } __u =	\
+		{ .__val = (val) }; 			\
+	__write_once_size(&(x), __u.__c, sizeof(x));	\
+	__u.__val;					\
+})
+
+/*
+ * log2_u32 - Compute the base 2 logarithm of a 32-bit exponential value.
+ * @v: The value for which we're computing the base 2 logarithm.
+ */
+static inline u32 log2_u32(u32 v)
+{
+        u32 r;
+        u32 shift;
+
+        r = (v > 0xFFFF) << 4; v >>= r;
+        shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+        shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+        shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+        r |= (v >> 1);
+        return r;
+}
+
+/*
+ * log2_u64 - Compute the base 2 logarithm of a 64-bit exponential value.
+ * @v: The value for which we're computing the base 2 logarithm.
+ */
+static inline u32 log2_u64(u64 v)
+{
+        u32 hi = v >> 32;
+        if (hi)
+                return log2_u32(hi) + 32 + 1;
+        else
+                return log2_u32(v) + 1;
+}
+
+#include "compat.bpf.h"
+
+#endif	/* __SCX_COMMON_BPF_H */

src/44-scx-simple/include/scx/common.h

@@ -0,0 +1,75 @@
+/* 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 __SCHED_EXT_COMMON_H
+#define __SCHED_EXT_COMMON_H
+
+#ifdef __KERNEL__
+#error "Should not be included by BPF programs"
+#endif
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <errno.h>
+
+typedef uint8_t u8;
+typedef uint16_t u16;
+typedef uint32_t u32;
+typedef uint64_t u64;
+typedef int8_t s8;
+typedef int16_t s16;
+typedef int32_t s32;
+typedef int64_t s64;
+
+#define SCX_BUG(__fmt, ...)							\
+	do {									\
+		fprintf(stderr, "[SCX_BUG] %s:%d", __FILE__, __LINE__);		\
+		if (errno)							\
+			fprintf(stderr, " (%s)\n", strerror(errno));		\
+		else								\
+			fprintf(stderr, "\n");					\
+		fprintf(stderr, __fmt __VA_OPT__(,) __VA_ARGS__);		\
+		fprintf(stderr, "\n");						\
+										\
+		exit(EXIT_FAILURE);						\
+	} while (0)
+
+#define SCX_BUG_ON(__cond, __fmt, ...)					\
+	do {								\
+		if (__cond)						\
+			SCX_BUG((__fmt) __VA_OPT__(,) __VA_ARGS__);	\
+	} while (0)
+
+/**
+ * RESIZE_ARRAY - Convenience macro for resizing a BPF array
+ * @__skel: the skeleton containing the array
+ * @elfsec: the data section of the BPF program in which the array exists
+ * @arr: the name of the array
+ * @n: the desired array element count
+ *
+ * For BPF arrays declared with RESIZABLE_ARRAY(), this macro performs two
+ * operations. It resizes the map which corresponds to the custom data
+ * section that contains the target array. As a side effect, the BTF info for
+ * the array is adjusted so that the array length is sized to cover the new
+ * data section size. The second operation is reassigning the skeleton pointer
+ * for that custom data section so that it points to the newly memory mapped
+ * region.
+ */
+#define RESIZE_ARRAY(__skel, elfsec, arr, n)						\
+	do {										\
+		size_t __sz;								\
+		bpf_map__set_value_size((__skel)->maps.elfsec##_##arr,			\
+				sizeof((__skel)->elfsec##_##arr->arr[0]) * (n));	\
+		(__skel)->elfsec##_##arr =						\
+			bpf_map__initial_value((__skel)->maps.elfsec##_##arr, &__sz);	\
+	} while (0)
+
+#include "user_exit_info.h"
+#include "compat.h"
+
+#endif	/* __SCHED_EXT_COMMON_H */

src/44-scx-simple/include/scx/compat.bpf.h

@@ -0,0 +1,47 @@
+/* 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>
+ */
+#ifndef __SCX_COMPAT_BPF_H
+#define __SCX_COMPAT_BPF_H
+
+#define __COMPAT_ENUM_OR_ZERO(__type, __ent)					\
+({										\
+	__type __ret = 0;							\
+	if (bpf_core_enum_value_exists(__type, __ent))				\
+		__ret = __ent;							\
+	__ret;									\
+})
+
+/* v6.12: 819513666966 ("sched_ext: Add cgroup support") */
+#define __COMPAT_scx_bpf_task_cgroup(p)						\
+	(bpf_ksym_exists(scx_bpf_task_cgroup) ?					\
+	 scx_bpf_task_cgroup((p)) : NULL)
+
+/* v6.12: 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()") */
+#define __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(it, slice)			\
+	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_slice) ?			\
+	 scx_bpf_dispatch_from_dsq_set_slice((it), (slice)) : (void)0)
+#define __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(it, vtime)			\
+	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq_set_vtime) ?			\
+	 scx_bpf_dispatch_from_dsq_set_vtime((it), (vtime)) : (void)0)
+#define __COMPAT_scx_bpf_dispatch_from_dsq(it, p, dsq_id, enq_flags)		\
+	(bpf_ksym_exists(scx_bpf_dispatch_from_dsq) ?				\
+	 scx_bpf_dispatch_from_dsq((it), (p), (dsq_id), (enq_flags)) : false)
+#define __COMPAT_scx_bpf_dispatch_vtime_from_dsq(it, p, dsq_id, enq_flags)	\
+	(bpf_ksym_exists(scx_bpf_dispatch_vtime_from_dsq) ?			\
+	 scx_bpf_dispatch_vtime_from_dsq((it), (p), (dsq_id), (enq_flags)) : false)
+
+/*
+ * Define sched_ext_ops. This may be expanded to define multiple variants for
+ * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH().
+ */
+#define SCX_OPS_DEFINE(__name, ...)						\
+	SEC(".struct_ops.link")							\
+	struct sched_ext_ops __name = {						\
+		__VA_ARGS__,							\
+	};
+
+#endif	/* __SCX_COMPAT_BPF_H */

src/44-scx-simple/include/scx/compat.h

@@ -0,0 +1,186 @@
+/* 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>
+ */
+#ifndef __SCX_COMPAT_H
+#define __SCX_COMPAT_H
+
+#include <bpf/btf.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+struct btf *__COMPAT_vmlinux_btf __attribute__((weak));
+
+static inline void __COMPAT_load_vmlinux_btf(void)
+{
+	if (!__COMPAT_vmlinux_btf) {
+		__COMPAT_vmlinux_btf = btf__load_vmlinux_btf();
+		SCX_BUG_ON(!__COMPAT_vmlinux_btf, "btf__load_vmlinux_btf()");
+	}
+}
+
+static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v)
+{
+	const struct btf_type *t;
+	const char *n;
+	s32 tid;
+	int i;
+
+	__COMPAT_load_vmlinux_btf();
+
+	tid = btf__find_by_name(__COMPAT_vmlinux_btf, type);
+	if (tid < 0)
+		return false;
+
+	t = btf__type_by_id(__COMPAT_vmlinux_btf, tid);
+	SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid);
+
+	if (btf_is_enum(t)) {
+		struct btf_enum *e = btf_enum(t);
+
+		for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+			n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off);
+			SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, name)) {
+				*v = e[i].val;
+				return true;
+			}
+		}
+	} else if (btf_is_enum64(t)) {
+		struct btf_enum64 *e = btf_enum64(t);
+
+		for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+			n = btf__name_by_offset(__COMPAT_vmlinux_btf, e[i].name_off);
+			SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, name)) {
+				*v = btf_enum64_value(&e[i]);
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+#define __COMPAT_ENUM_OR_ZERO(__type, __ent)					\
+({										\
+	u64 __val = 0;								\
+	__COMPAT_read_enum(__type, __ent, &__val);				\
+	__val;									\
+})
+
+static inline bool __COMPAT_has_ksym(const char *ksym)
+{
+	__COMPAT_load_vmlinux_btf();
+	return btf__find_by_name(__COMPAT_vmlinux_btf, ksym) >= 0;
+}
+
+static inline bool __COMPAT_struct_has_field(const char *type, const char *field)
+{
+	const struct btf_type *t;
+	const struct btf_member *m;
+	const char *n;
+	s32 tid;
+	int i;
+
+	__COMPAT_load_vmlinux_btf();
+	tid = btf__find_by_name_kind(__COMPAT_vmlinux_btf, type, BTF_KIND_STRUCT);
+	if (tid < 0)
+		return false;
+
+	t = btf__type_by_id(__COMPAT_vmlinux_btf, tid);
+	SCX_BUG_ON(!t, "btf__type_by_id(%d)", tid);
+
+	m = btf_members(t);
+
+	for (i = 0; i < BTF_INFO_VLEN(t->info); i++) {
+		n = btf__name_by_offset(__COMPAT_vmlinux_btf, m[i].name_off);
+		SCX_BUG_ON(!n, "btf__name_by_offset()");
+			if (!strcmp(n, field))
+				return true;
+	}
+
+	return false;
+}
+
+#define SCX_OPS_SWITCH_PARTIAL							\
+	__COMPAT_ENUM_OR_ZERO("scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL")
+
+static inline long scx_hotplug_seq(void)
+{
+	int fd;
+	char buf[32];
+	ssize_t len;
+	long val;
+
+	fd = open("/sys/kernel/sched_ext/hotplug_seq", O_RDONLY);
+	if (fd < 0)
+		return -ENOENT;
+
+	len = read(fd, buf, sizeof(buf) - 1);
+	SCX_BUG_ON(len <= 0, "read failed (%ld)", len);
+	buf[len] = 0;
+	close(fd);
+
+	val = strtoul(buf, NULL, 10);
+	SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val);
+
+	return val;
+}
+
+/*
+ * struct sched_ext_ops can change over time. If compat.bpf.h::SCX_OPS_DEFINE()
+ * is used to define ops and compat.h::SCX_OPS_LOAD/ATTACH() are used to load
+ * and attach it, backward compatibility is automatically maintained where
+ * reasonable.
+ *
+ * ec7e3b0463e1 ("implement-ops") in https://github.com/sched-ext/sched_ext is
+ * the current minimum required kernel version.
+ */
+#define SCX_OPS_OPEN(__ops_name, __scx_name) ({					\
+	struct __scx_name *__skel;						\
+										\
+	SCX_BUG_ON(!__COMPAT_struct_has_field("sched_ext_ops", "dump"),		\
+		   "sched_ext_ops.dump() missing, kernel too old?");		\
+										\
+	__skel = __scx_name##__open();						\
+	SCX_BUG_ON(!__skel, "Could not open " #__scx_name);			\
+	__skel->struct_ops.__ops_name->hotplug_seq = scx_hotplug_seq();		\
+	__skel; 								\
+})
+
+#define SCX_OPS_LOAD(__skel, __ops_name, __scx_name, __uei_name) ({		\
+	UEI_SET_SIZE(__skel, __ops_name, __uei_name);				\
+	SCX_BUG_ON(__scx_name##__load((__skel)), "Failed to load skel");	\
+})
+
+/*
+ * New versions of bpftool now emit additional link placeholders for BPF maps,
+ * and set up BPF skeleton in such a way that libbpf will auto-attach BPF maps
+ * automatically, assumming libbpf is recent enough (v1.5+). Old libbpf will do
+ * nothing with those links and won't attempt to auto-attach maps.
+ *
+ * To maintain compatibility with older libbpf while avoiding trying to attach
+ * twice, disable the autoattach feature on newer libbpf.
+ */
+#if LIBBPF_MAJOR_VERSION > 1 ||							\
+	(LIBBPF_MAJOR_VERSION == 1 && LIBBPF_MINOR_VERSION >= 5)
+#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name)			\
+	bpf_map__set_autoattach((__skel)->maps.__ops_name, false)
+#else
+#define __SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name) do {} while (0)
+#endif
+
+#define SCX_OPS_ATTACH(__skel, __ops_name, __scx_name) ({			\
+	struct bpf_link *__link;						\
+	__SCX_OPS_DISABLE_AUTOATTACH(__skel, __ops_name);			\
+	SCX_BUG_ON(__scx_name##__attach((__skel)), "Failed to attach skel");	\
+	__link = bpf_map__attach_struct_ops((__skel)->maps.__ops_name);		\
+	SCX_BUG_ON(!__link, "Failed to attach struct_ops");			\
+	__link;									\
+})
+
+#endif	/* __SCX_COMPAT_H */

src/44-scx-simple/include/scx/user_exit_info.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Define struct user_exit_info which is shared between BPF and userspace parts
+ * to communicate exit status and other information.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#ifndef __USER_EXIT_INFO_H
+#define __USER_EXIT_INFO_H
+
+enum uei_sizes {
+	UEI_REASON_LEN		= 128,
+	UEI_MSG_LEN		= 1024,
+	UEI_DUMP_DFL_LEN	= 32768,
+};
+
+struct user_exit_info {
+	int		kind;
+	s64		exit_code;
+	char		reason[UEI_REASON_LEN];
+	char		msg[UEI_MSG_LEN];
+};
+
+#ifdef __bpf__
+
+#ifdef LSP
+#include "../vmlinux/vmlinux.h"
+#else
+#include "vmlinux.h"
+#endif
+#include <bpf/bpf_core_read.h>
+
+#define UEI_DEFINE(__name)							\
+	char RESIZABLE_ARRAY(data, __name##_dump);				\
+	const volatile u32 __name##_dump_len;					\
+	struct user_exit_info __name SEC(".data")
+
+#define UEI_RECORD(__uei_name, __ei) ({						\
+	bpf_probe_read_kernel_str(__uei_name.reason,				\
+				  sizeof(__uei_name.reason), (__ei)->reason);	\
+	bpf_probe_read_kernel_str(__uei_name.msg,				\
+				  sizeof(__uei_name.msg), (__ei)->msg);		\
+	bpf_probe_read_kernel_str(__uei_name##_dump,				\
+				  __uei_name##_dump_len, (__ei)->dump);		\
+	if (bpf_core_field_exists((__ei)->exit_code))				\
+		__uei_name.exit_code = (__ei)->exit_code;			\
+	/* use __sync to force memory barrier */				\
+	__sync_val_compare_and_swap(&__uei_name.kind, __uei_name.kind,		\
+				    (__ei)->kind);				\
+})
+
+#else	/* !__bpf__ */
+
+#include <stdio.h>
+#include <stdbool.h>
+
+/* no need to call the following explicitly if SCX_OPS_LOAD() is used */
+#define UEI_SET_SIZE(__skel, __ops_name, __uei_name) ({					\
+	u32 __len = (__skel)->struct_ops.__ops_name->exit_dump_len ?: UEI_DUMP_DFL_LEN;	\
+	(__skel)->rodata->__uei_name##_dump_len = __len;				\
+	RESIZE_ARRAY((__skel), data, __uei_name##_dump, __len);				\
+})
+
+#define UEI_EXITED(__skel, __uei_name) ({					\
+	/* use __sync to force memory barrier */				\
+	__sync_val_compare_and_swap(&(__skel)->data->__uei_name.kind, -1, -1);	\
+})
+
+#define UEI_REPORT(__skel, __uei_name) ({					\
+	struct user_exit_info *__uei = &(__skel)->data->__uei_name;		\
+	char *__uei_dump = (__skel)->data_##__uei_name##_dump->__uei_name##_dump; \
+	if (__uei_dump[0] != '\0') {						\
+		fputs("\nDEBUG DUMP\n", stderr);				\
+		fputs("================================================================================\n\n", stderr); \
+		fputs(__uei_dump, stderr);					\
+		fputs("\n================================================================================\n\n", stderr); \
+	}									\
+	fprintf(stderr, "EXIT: %s", __uei->reason);				\
+	if (__uei->msg[0] != '\0')						\
+		fprintf(stderr, " (%s)", __uei->msg);				\
+	fputs("\n", stderr);							\
+	__uei->exit_code;							\
+})
+
+/*
+ * We can't import vmlinux.h while compiling user C code. Let's duplicate
+ * scx_exit_code definition.
+ */
+enum scx_exit_code {
+	/* Reasons */
+	SCX_ECODE_RSN_HOTPLUG		= 1LLU << 32,
+
+	/* Actions */
+	SCX_ECODE_ACT_RESTART		= 1LLU << 48,
+};
+
+enum uei_ecode_mask {
+	UEI_ECODE_USER_MASK		= ((1LLU << 32) - 1),
+	UEI_ECODE_SYS_RSN_MASK		= ((1LLU << 16) - 1) << 32,
+	UEI_ECODE_SYS_ACT_MASK		= ((1LLU << 16) - 1) << 48,
+};
+
+/*
+ * These macro interpret the ecode returned from UEI_REPORT().
+ */
+#define UEI_ECODE_USER(__ecode)		((__ecode) & UEI_ECODE_USER_MASK)
+#define UEI_ECODE_SYS_RSN(__ecode)	((__ecode) & UEI_ECODE_SYS_RSN_MASK)
+#define UEI_ECODE_SYS_ACT(__ecode)	((__ecode) & UEI_ECODE_SYS_ACT_MASK)
+
+#define UEI_ECODE_RESTART(__ecode)	(UEI_ECODE_SYS_ACT((__ecode)) == SCX_ECODE_ACT_RESTART)
+
+#endif	/* __bpf__ */
+#endif	/* __USER_EXIT_INFO_H */

src/44-scx-simple/scx_simple.bpf.c

@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple scheduler.
+ *
+ * By default, it operates as a simple global weighted vtime scheduler and can
+ * be switched to FIFO scheduling. It also demonstrates the following niceties.
+ *
+ * - Statistics tracking how many tasks are queued to local and global dsq's.
+ * - Termination notification for userspace.
+ *
+ * While very simple, this scheduler should work reasonably well on CPUs with a
+ * uniform L3 cache topology. While preemption is not implemented, the fact that
+ * the scheduling queue is shared across all CPUs means that whatever is at the
+ * front of the queue is likely to be executed fairly quickly given enough
+ * number of CPUs. The FIFO scheduling mode may be beneficial to some workloads
+ * but comes with the usual problems with FIFO scheduling where saturating
+ * threads can easily drown out interactive ones.
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile bool fifo_sched;
+
+static u64 vtime_now;
+UEI_DEFINE(uei);
+
+/*
+ * Built-in DSQs such as SCX_DSQ_GLOBAL cannot be used as priority queues
+ * (meaning, cannot be dispatched to with scx_bpf_dispatch_vtime()). We
+ * therefore create a separate DSQ with ID 0 that we dispatch to and consume
+ * from. If scx_simple only supported global FIFO scheduling, then we could
+ * just use SCX_DSQ_GLOBAL.
+ */
+#define SHARED_DSQ 0
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+	__uint(max_entries, 2);			/* [local, global] */
+} stats SEC(".maps");
+
+static void stat_inc(u32 idx)
+{
+	u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx);
+	if (cnt_p)
+		(*cnt_p)++;
+}
+
+static inline bool vtime_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	bool is_idle = false;
+	s32 cpu;
+
+	cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle);
+	if (is_idle) {
+		stat_inc(0);	/* count local queueing */
+		scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+	}
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	stat_inc(1);	/* count global queueing */
+
+	if (fifo_sched) {
+		scx_bpf_dispatch(p, SHARED_DSQ, SCX_SLICE_DFL, enq_flags);
+	} else {
+		u64 vtime = p->scx.dsq_vtime;
+
+		/*
+		 * Limit the amount of budget that an idling task can accumulate
+		 * to one slice.
+		 */
+		if (vtime_before(vtime, vtime_now - SCX_SLICE_DFL))
+			vtime = vtime_now - SCX_SLICE_DFL;
+
+		scx_bpf_dispatch_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime,
+				       enq_flags);
+	}
+}
+
+void BPF_STRUCT_OPS(simple_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_consume(SHARED_DSQ);
+}
+
+void BPF_STRUCT_OPS(simple_running, struct task_struct *p)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Global vtime always progresses forward as tasks start executing. The
+	 * test and update can be performed concurrently from multiple CPUs and
+	 * thus racy. Any error should be contained and temporary. Let's just
+	 * live with it.
+	 */
+	if (vtime_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(simple_stopping, struct task_struct *p, bool runnable)
+{
+	if (fifo_sched)
+		return;
+
+	/*
+	 * Scale the execution time by the inverse of the weight and charge.
+	 *
+	 * Note that the default yield implementation yields by setting
+	 * @p->scx.slice to zero and the following would treat the yielding task
+	 * as if it has consumed all its slice. If this penalizes yielding tasks
+	 * too much, determine the execution time by taking explicit timestamps
+	 * instead of depending on @p->scx.slice.
+	 */
+	p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+}
+
+void BPF_STRUCT_OPS(simple_enable, struct task_struct *p)
+{
+	p->scx.dsq_vtime = vtime_now;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init)
+{
+	return scx_bpf_create_dsq(SHARED_DSQ, -1);
+}
+
+void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(simple_ops,
+	       .select_cpu		= (void *)simple_select_cpu,
+	       .enqueue			= (void *)simple_enqueue,
+	       .dispatch		= (void *)simple_dispatch,
+	       .running			= (void *)simple_running,
+	       .stopping		= (void *)simple_stopping,
+	       .enable			= (void *)simple_enable,
+	       .init			= (void *)simple_init,
+	       .exit			= (void *)simple_exit,
+	       .name			= "simple");

src/44-scx-simple/scx_simple.c

@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_simple.skel.h"
+
+const char help_fmt[] =
+"A simple sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-f] [-v]\n"
+"\n"
+"  -f            Use FIFO scheduling instead of weighted vtime scheduling\n"
+"  -v            Print libbpf debug messages\n"
+"  -h            Display this help and exit\n";
+
+static bool verbose;
+static volatile int exit_req;
+
+static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !verbose)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static void sigint_handler(int simple)
+{
+	exit_req = 1;
+}
+
+static void read_stats(struct scx_simple *skel, __u64 *stats)
+{
+	int nr_cpus = libbpf_num_possible_cpus();
+	__u64 cnts[2][nr_cpus];
+	__u32 idx;
+
+	memset(stats, 0, sizeof(stats[0]) * 2);
+
+	for (idx = 0; idx < 2; idx++) {
+		int ret, cpu;
+
+		ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats),
+					  &idx, cnts[idx]);
+		if (ret < 0)
+			continue;
+		for (cpu = 0; cpu < nr_cpus; cpu++)
+			stats[idx] += cnts[idx][cpu];
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct scx_simple *skel;
+	struct bpf_link *link;
+	__u32 opt;
+	__u64 ecode;
+
+	libbpf_set_print(libbpf_print_fn);
+	signal(SIGINT, sigint_handler);
+	signal(SIGTERM, sigint_handler);
+restart:
+	skel = SCX_OPS_OPEN(simple_ops, scx_simple);
+
+	while ((opt = getopt(argc, argv, "fvh")) != -1) {
+		switch (opt) {
+		case 'f':
+			skel->rodata->fifo_sched = true;
+			break;
+		case 'v':
+			verbose = true;
+			break;
+		default:
+			fprintf(stderr, help_fmt, basename(argv[0]));
+			return opt != 'h';
+		}
+	}
+
+	SCX_OPS_LOAD(skel, simple_ops, scx_simple, uei);
+	link = SCX_OPS_ATTACH(skel, simple_ops, scx_simple);
+
+	while (!exit_req && !UEI_EXITED(skel, uei)) {
+		__u64 stats[2];
+
+		read_stats(skel, stats);
+		printf("local=%llu global=%llu\n", stats[0], stats[1]);
+		fflush(stdout);
+		sleep(1);
+	}
+
+	bpf_link__destroy(link);
+	ecode = UEI_REPORT(skel, uei);
+	scx_simple__destroy(skel);
+
+	if (UEI_ECODE_RESTART(ecode))
+		goto restart;
+	return 0;
+}

src/SUMMARY_en.md

@@ -79,6 +79,7 @@ Other:
 - [Using user ring buffer to send information to the kernel](35-user-ringbuf/README.md)
 - [Userspace eBPF Runtimes: Overview and Applications](36-userspace-ebpf/README.md)
 - [Compile Once, Run Everywhere for userspace with eBPF and BTF](38-btf-uprobe/README.md)
+- [Extending eBPF Beyond Its Limits: Custom kfuncs in Kernel Modules](43-kfuncs/README.md)
 
 # bcc and bpftrace tutorial
 

src/guideline_advance.md

@@ -0,0 +1,81 @@
+# Blog Guidelines for Advanced eBPF Tutorials
+
+This document outlines the key patterns and requirements for writing advanced eBPF tutorials. Advanced tutorials focus on complex eBPF programs, tools, or features that extend beyond basic concepts. They require a deeper understanding of eBPF and kernel interactions.
+
+The audience for advanced tutorials includes developers, system administrators, and security professionals with intermediate to advanced eBPF knowledge. The goal is to provide in-depth explanations of advanced eBPF topics and practical examples that readers can apply in real-world scenarios.
+
+The key point in tone: Using oral English, clear and simple words and short sentence, make it attractive and easy to read, do not make it like a paper. Not too much fancy words, try to be attracive.
+
+You should also include all the details and information I provide to you. do not simplify or change any of them, you just need to regorganize them in a more attractive way as a tutorial blog.
+
+## starting with a clear and descriptive title
+
+Begin with a clear and descriptive title:
+
+```
+# eBPF Tutorial by Example: [Advanced Topic]
+```
+
+Kick off with a brief intro to the advanced eBPF topic you're covering, and the example or tool you'll discuss. Highlight its significance and how it extends beyond basic concepts. Let readers know what they'll learn and why it's important.
+
+## Incroduction to the concept, tool and Background
+
+(Come up with a better session title)
+
+Provide an overview of the specific eBPF programs, tools, or features you'll discuss. Explain their purpose, use cases, and the key eBPF features or kernel events involved. Focus on aspects that are crucial for advanced understanding.
+
+## High-Level Code Analysis
+
+Dive into the kernel-mode eBPF code and user-space code, focusing on high-level concepts rather than basic syntax.
+
+Always include the full code as it is first. then break down the key parts.
+
+Try to avoid using too much list, make it more like a story.
+
+Follow the steps:
+
+1. First, introduce The overall processing logic in both kernel and user space.
+2. Then break down the kernel-mode eBPF code, include
+
+- How the eBPF program is structured.
+- Key eBPF functionalities utilized.
+- How the code interacts with kernel events.
+
+Do not make them a list, make them some paragraphs, you can also quote some code snippets to explain the key parts of the code if needed, focus on the logic and features used in advanced eBPF development. Don't make it too long, but make sure it is informative enough and you explain everything a advanced eBPF developer wants to know.
+
+3. Then briefly explain the user-space code
+
+Aim to help readers grasp how the code works without getting bogged down in basic details.
+
+## Any more detailed concepts or features explanation
+
+If there are other information or features that are important to understand the code, you can add them here.
+
+## 5. Compilation and Execution
+
+Provide instructions on compiling and running the eBPF programs, noting any advanced configurations or dependencies. Include commands and what readers should expect as output. Typically, you can run `make` in the relevant directory in the tutorial repository to build the code.
+
+Include links to complete source code and resources:
+
+- **Repository:** <https://github.com/eunomia-bpf/bpf-developer-tutorial>
+- **Website:** <https://eunomia.dev/tutorials/>
+
+## 6. Summary and Call to Action
+
+Wrap up by summarizing the key points. Emphasize the advanced concepts covered and encourage readers to apply this knowledge. Invite them to explore more examples and tutorials, as one paragraph:
+
+> If you'd like to dive deeper into eBPF, check out our tutorial repository at <https://github.com/eunomia-bpf/bpf-developer-tutorial> or visit our website at <https://eunomia.dev/tutorials/>.
+
+## reference
+
+You should include the important references and resources that used in the tutorial. If this is from other sources like kernel sample or tools, make sure to include them here and clearly mention them in the tutorial.
+
+## Additional Guidelines
+
+- **Clarity:** Use simple language and short sentences to explain complex ideas. But the information should be complete and detailed.
+- **Focus on Advanced Concepts:** Assume readers have basic eBPF knowledge; skip elementary explanations.
+- **Engagement:** Encourage readers to think critically and engage with the material.
+- **Consistency:** Keep a consistent style and formatting throughout.
+- **Code Formatting:** Ensure code snippets are well-formatted and highlight key parts. Do not change or simplify any of the code and commands, keep them as they are.
+- **Proofreading:** Double-check for errors and ensure technical accuracy.
+- **Accessibility:** Make the content valuable for readers with advanced expertise, avoiding unnecessary simplifications.

src/guideline_basic.md

@@ -111,8 +111,4 @@ You need to have **Call to Action** in Summary and Conclusion
 
 Also, do not just list points, try to make it using paragraph unless points list is clear. 
 
-**The key point in tone: Using oral English, clear and simple words and short sentence, make it attractive and easy to read, do not make it like a paper. Not too much fancy words, try to be attracive**
-
-## Template Summary
-
-By following this pattern, anyone tasked with writing future blog posts will have a clear structure to adhere to, ensuring that all necessary information is included and presented in a logical order.
+The key point in tone: Using oral English, clear and simple words and short sentence, make it attractive and easy to read, do not make it like a paper. Not too much fancy words, try to be attracive.