kernel-packages/linux-pikaos-6.11.8
2
0
Fork 0
generated from kernel-packages/linux-pikaos-template
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
e0b5d6af41
linux-pikaos-6.11.8/patches/0002-sched-ext.patch

17926 lines
527 KiB
Diff
Raw Blame History

From c0d9f38dcc2b6bb16e54e7f438c9c449319ebef4 Mon Sep 17 00:00:00 2001
From: Peter Jung <admin@ptr1337.dev>
Date: Thu, 10 Oct 2024 12:47:12 +0200
Subject: [PATCH] sched-ext
Signed-off-by: Peter Jung <admin@ptr1337.dev>
---
Documentation/scheduler/index.rst | 1 +
Documentation/scheduler/sched-ext.rst | 326 +
MAINTAINERS | 13 +
drivers/tty/sysrq.c | 1 +
include/asm-generic/vmlinux.lds.h | 1 +
include/linux/cgroup.h | 4 +-
include/linux/sched.h | 5 +
include/linux/sched/ext.h | 216 +
include/linux/sched/task.h | 8 +-
include/trace/events/sched_ext.h | 32 +
include/uapi/linux/sched.h | 1 +
init/Kconfig | 10 +
init/init_task.c | 12 +
kernel/Kconfig.preempt | 27 +-
kernel/fork.c | 17 +-
kernel/sched/build_policy.c | 11 +
kernel/sched/core.c | 288 +-
kernel/sched/cpufreq_schedutil.c | 50 +-
kernel/sched/debug.c | 3 +
kernel/sched/ext.c | 7281 +++++++++++++++++
kernel/sched/ext.h | 91 +
kernel/sched/fair.c | 21 +-
kernel/sched/idle.c | 2 +
kernel/sched/sched.h | 203 +-
kernel/sched/syscalls.c | 26 +
lib/dump_stack.c | 1 +
tools/Makefile | 10 +-
tools/sched_ext/.gitignore | 2 +
tools/sched_ext/Makefile | 246 +
tools/sched_ext/README.md | 270 +
.../sched_ext/include/bpf-compat/gnu/stubs.h | 11 +
tools/sched_ext/include/scx/common.bpf.h | 427 +
tools/sched_ext/include/scx/common.h | 75 +
tools/sched_ext/include/scx/compat.bpf.h | 47 +
tools/sched_ext/include/scx/compat.h | 186 +
tools/sched_ext/include/scx/user_exit_info.h | 115 +
tools/sched_ext/scx_central.bpf.c | 361 +
tools/sched_ext/scx_central.c | 135 +
tools/sched_ext/scx_flatcg.bpf.c | 957 +++
tools/sched_ext/scx_flatcg.c | 233 +
tools/sched_ext/scx_flatcg.h | 51 +
tools/sched_ext/scx_qmap.bpf.c | 813 ++
tools/sched_ext/scx_qmap.c | 153 +
tools/sched_ext/scx_show_state.py | 40 +
tools/sched_ext/scx_simple.bpf.c | 156 +
tools/sched_ext/scx_simple.c | 107 +
tools/testing/selftests/sched_ext/.gitignore | 6 +
tools/testing/selftests/sched_ext/Makefile | 218 +
tools/testing/selftests/sched_ext/config | 9 +
.../selftests/sched_ext/create_dsq.bpf.c | 58 +
.../testing/selftests/sched_ext/create_dsq.c | 57 +
.../sched_ext/ddsp_bogus_dsq_fail.bpf.c | 42 +
.../selftests/sched_ext/ddsp_bogus_dsq_fail.c | 57 +
.../sched_ext/ddsp_vtimelocal_fail.bpf.c | 39 +
.../sched_ext/ddsp_vtimelocal_fail.c | 56 +
.../selftests/sched_ext/dsp_local_on.bpf.c | 65 +
.../selftests/sched_ext/dsp_local_on.c | 58 +
.../sched_ext/enq_last_no_enq_fails.bpf.c | 21 +
.../sched_ext/enq_last_no_enq_fails.c | 60 +
.../sched_ext/enq_select_cpu_fails.bpf.c | 43 +
.../sched_ext/enq_select_cpu_fails.c | 61 +
tools/testing/selftests/sched_ext/exit.bpf.c | 84 +
tools/testing/selftests/sched_ext/exit.c | 55 +
tools/testing/selftests/sched_ext/exit_test.h | 20 +
.../testing/selftests/sched_ext/hotplug.bpf.c | 61 +
tools/testing/selftests/sched_ext/hotplug.c | 168 +
.../selftests/sched_ext/hotplug_test.h | 15 +
.../sched_ext/init_enable_count.bpf.c | 53 +
.../selftests/sched_ext/init_enable_count.c | 166 +
.../testing/selftests/sched_ext/maximal.bpf.c | 164 +
tools/testing/selftests/sched_ext/maximal.c | 51 +
.../selftests/sched_ext/maybe_null.bpf.c | 36 +
.../testing/selftests/sched_ext/maybe_null.c | 49 +
.../sched_ext/maybe_null_fail_dsp.bpf.c | 25 +
.../sched_ext/maybe_null_fail_yld.bpf.c | 28 +
.../testing/selftests/sched_ext/minimal.bpf.c | 21 +
tools/testing/selftests/sched_ext/minimal.c | 58 +
.../selftests/sched_ext/prog_run.bpf.c | 33 +
tools/testing/selftests/sched_ext/prog_run.c | 78 +
.../testing/selftests/sched_ext/reload_loop.c | 75 +
tools/testing/selftests/sched_ext/runner.c | 201 +
tools/testing/selftests/sched_ext/scx_test.h | 131 +
.../selftests/sched_ext/select_cpu_dfl.bpf.c | 40 +
.../selftests/sched_ext/select_cpu_dfl.c | 72 +
.../sched_ext/select_cpu_dfl_nodispatch.bpf.c | 89 +
.../sched_ext/select_cpu_dfl_nodispatch.c | 72 +
.../sched_ext/select_cpu_dispatch.bpf.c | 41 +
.../selftests/sched_ext/select_cpu_dispatch.c | 70 +
.../select_cpu_dispatch_bad_dsq.bpf.c | 37 +
.../sched_ext/select_cpu_dispatch_bad_dsq.c | 56 +
.../select_cpu_dispatch_dbl_dsp.bpf.c | 38 +
.../sched_ext/select_cpu_dispatch_dbl_dsp.c | 56 +
.../sched_ext/select_cpu_vtime.bpf.c | 92 +
.../selftests/sched_ext/select_cpu_vtime.c | 59 +
.../selftests/sched_ext/test_example.c | 49 +
tools/testing/selftests/sched_ext/util.c | 71 +
tools/testing/selftests/sched_ext/util.h | 13 +
97 files changed, 16193 insertions(+), 130 deletions(-)
create mode 100644 Documentation/scheduler/sched-ext.rst
create mode 100644 include/linux/sched/ext.h
create mode 100644 include/trace/events/sched_ext.h
create mode 100644 kernel/sched/ext.c
create mode 100644 kernel/sched/ext.h
create mode 100644 tools/sched_ext/.gitignore
create mode 100644 tools/sched_ext/Makefile
create mode 100644 tools/sched_ext/README.md
create mode 100644 tools/sched_ext/include/bpf-compat/gnu/stubs.h
create mode 100644 tools/sched_ext/include/scx/common.bpf.h
create mode 100644 tools/sched_ext/include/scx/common.h
create mode 100644 tools/sched_ext/include/scx/compat.bpf.h
create mode 100644 tools/sched_ext/include/scx/compat.h
create mode 100644 tools/sched_ext/include/scx/user_exit_info.h
create mode 100644 tools/sched_ext/scx_central.bpf.c
create mode 100644 tools/sched_ext/scx_central.c
create mode 100644 tools/sched_ext/scx_flatcg.bpf.c
create mode 100644 tools/sched_ext/scx_flatcg.c
create mode 100644 tools/sched_ext/scx_flatcg.h
create mode 100644 tools/sched_ext/scx_qmap.bpf.c
create mode 100644 tools/sched_ext/scx_qmap.c
create mode 100644 tools/sched_ext/scx_show_state.py
create mode 100644 tools/sched_ext/scx_simple.bpf.c
create mode 100644 tools/sched_ext/scx_simple.c
create mode 100644 tools/testing/selftests/sched_ext/.gitignore
create mode 100644 tools/testing/selftests/sched_ext/Makefile
create mode 100644 tools/testing/selftests/sched_ext/config
create mode 100644 tools/testing/selftests/sched_ext/create_dsq.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/create_dsq.c
create mode 100644 tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c
create mode 100644 tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
create mode 100644 tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/dsp_local_on.c
create mode 100644 tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
create mode 100644 tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
create mode 100644 tools/testing/selftests/sched_ext/exit.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/exit.c
create mode 100644 tools/testing/selftests/sched_ext/exit_test.h
create mode 100644 tools/testing/selftests/sched_ext/hotplug.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/hotplug.c
create mode 100644 tools/testing/selftests/sched_ext/hotplug_test.h
create mode 100644 tools/testing/selftests/sched_ext/init_enable_count.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/init_enable_count.c
create mode 100644 tools/testing/selftests/sched_ext/maximal.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/maximal.c
create mode 100644 tools/testing/selftests/sched_ext/maybe_null.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/maybe_null.c
create mode 100644 tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/minimal.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/minimal.c
create mode 100644 tools/testing/selftests/sched_ext/prog_run.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/prog_run.c
create mode 100644 tools/testing/selftests/sched_ext/reload_loop.c
create mode 100644 tools/testing/selftests/sched_ext/runner.c
create mode 100644 tools/testing/selftests/sched_ext/scx_test.h
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
create mode 100644 tools/testing/selftests/sched_ext/select_cpu_vtime.c
create mode 100644 tools/testing/selftests/sched_ext/test_example.c
create mode 100644 tools/testing/selftests/sched_ext/util.c
create mode 100644 tools/testing/selftests/sched_ext/util.h
diff --git a/Documentation/scheduler/index.rst b/Documentation/scheduler/index.rst
index 43bd8a145b7a..0611dc3dda8e 100644
--- a/Documentation/scheduler/index.rst
+++ b/Documentation/scheduler/index.rst
@@ -20,6 +20,7 @@ Scheduler
sched-nice-design
sched-rt-group
sched-stats
+ sched-ext
sched-debug
text_files
diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
new file mode 100644
index 000000000000..6c0d70e2e27d
--- /dev/null
+++ b/Documentation/scheduler/sched-ext.rst
@@ -0,0 +1,326 @@
+==========================
+Extensible Scheduler Class
+==========================
+
+sched_ext is a scheduler class whose behavior can be defined by a set of BPF
+programs - the BPF scheduler.
+
+* sched_ext exports a full scheduling interface so that any scheduling
+ algorithm can be implemented on top.
+
+* The BPF scheduler can group CPUs however it sees fit and schedule them
+ together, as tasks aren't tied to specific CPUs at the time of wakeup.
+
+* The BPF scheduler can be turned on and off dynamically anytime.
+
+* The system integrity is maintained no matter what the BPF scheduler does.
+ The default scheduling behavior is restored anytime an error is detected,
+ a runnable task stalls, or on invoking the SysRq key sequence
+ :kbd:`SysRq-S`.
+
+* When the BPF scheduler triggers an error, debug information is dumped to
+ aid debugging. The debug dump is passed to and printed out by the
+ scheduler binary. The debug dump can also be accessed through the
+ `sched_ext_dump` tracepoint. The SysRq key sequence :kbd:`SysRq-D`
+ triggers a debug dump. This doesn't terminate the BPF scheduler and can
+ only be read through the tracepoint.
+
+Switching to and from sched_ext
+===============================
+
+``CONFIG_SCHED_CLASS_EXT`` is the config option to enable sched_ext and
+``tools/sched_ext`` contains the example schedulers. The following config
+options should be enabled to use sched_ext:
+
+.. code-block:: none
+
+ 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
+
+sched_ext is used only when the BPF scheduler is loaded and running.
+
+If a task explicitly sets its scheduling policy to ``SCHED_EXT``, it will be
+treated as ``SCHED_NORMAL`` and scheduled by CFS until the BPF scheduler is
+loaded.
+
+When the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is not set
+in ``ops->flags``, all ``SCHED_NORMAL``, ``SCHED_BATCH``, ``SCHED_IDLE``, and
+``SCHED_EXT`` tasks are scheduled by sched_ext.
+
+However, when the BPF scheduler is loaded and ``SCX_OPS_SWITCH_PARTIAL`` is
+set in ``ops->flags``, only tasks with the ``SCHED_EXT`` policy are scheduled
+by sched_ext, while tasks with ``SCHED_NORMAL``, ``SCHED_BATCH`` and
+``SCHED_IDLE`` policies are scheduled by CFS.
+
+Terminating the sched_ext scheduler program, triggering :kbd:`SysRq-S`, or
+detection of any internal error including stalled runnable tasks aborts the
+BPF scheduler and reverts all tasks back to CFS.
+
+.. code-block:: none
+
+ # make -j16 -C tools/sched_ext
+ # tools/sched_ext/scx_simple
+ local=0 global=3
+ local=5 global=24
+ local=9 global=44
+ local=13 global=56
+ local=17 global=72
+ ^CEXIT: BPF scheduler unregistered
+
+The current status of the BPF scheduler can be determined as follows:
+
+.. code-block:: none
+
+ # cat /sys/kernel/sched_ext/state
+ enabled
+ # cat /sys/kernel/sched_ext/root/ops
+ simple
+
+You can check if any BPF scheduler has ever been loaded since boot by examining
+this monotonically incrementing counter (a value of zero indicates that no BPF
+scheduler has been loaded):
+
+.. code-block:: none
+
+ # cat /sys/kernel/sched_ext/enable_seq
+ 1
+
+``tools/sched_ext/scx_show_state.py`` is a drgn script which shows more
+detailed information:
+
+.. code-block:: none
+
+ # tools/sched_ext/scx_show_state.py
+ ops : simple
+ enabled : 1
+ switching_all : 1
+ switched_all : 1
+ enable_state : enabled (2)
+ bypass_depth : 0
+ nr_rejected : 0
+ enable_seq : 1
+
+If ``CONFIG_SCHED_DEBUG`` is set, whether a given task is on sched_ext can
+be determined as follows:
+
+.. code-block:: none
+
+ # grep ext /proc/self/sched
+ ext.enabled : 1
+
+The Basics
+==========
+
+Userspace can implement an arbitrary BPF scheduler by loading a set of BPF
+programs that implement ``struct sched_ext_ops``. The only mandatory field
+is ``ops.name`` which must be a valid BPF object name. All operations are
+optional. The following modified excerpt is from
+``tools/sched_ext/scx_simple.bpf.c`` showing a minimal global FIFO scheduler.
+
+.. code-block:: c
+
+ /*
+ * Decide which CPU a task should be migrated to before being
+ * enqueued (either at wakeup, fork time, or exec time). If an
+ * idle core is found by the default ops.select_cpu() implementation,
+ * then dispatch the task directly to SCX_DSQ_LOCAL and skip the
+ * ops.enqueue() callback.
+ *
+ * Note that this implementation has exactly the same behavior as the
+ * default ops.select_cpu implementation. The behavior of the scheduler
+ * would be exactly same if the implementation just didn't define the
+ * simple_select_cpu() struct_ops prog.
+ */
+ s32 BPF_STRUCT_OPS(simple_select_cpu, struct task_struct *p,
+ s32 prev_cpu, u64 wake_flags)
+ {
+ s32 cpu;
+ /* Need to initialize or the BPF verifier will reject the program */
+ bool direct = false;
+
+ cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &direct);
+
+ if (direct)
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+
+ return cpu;
+ }
+
+ /*
+ * Do a direct dispatch of a task to the global DSQ. This ops.enqueue()
+ * callback will only be invoked if we failed to find a core to dispatch
+ * to in ops.select_cpu() above.
+ *
+ * Note that this implementation has exactly the same behavior as the
+ * default ops.enqueue implementation, which just dispatches the task
+ * to SCX_DSQ_GLOBAL. The behavior of the scheduler would be exactly same
+ * if the implementation just didn't define the simple_enqueue struct_ops
+ * prog.
+ */
+ void BPF_STRUCT_OPS(simple_enqueue, struct task_struct *p, u64 enq_flags)
+ {
+ scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ }
+
+ s32 BPF_STRUCT_OPS_SLEEPABLE(simple_init)
+ {
+ /*
+ * By default, all SCHED_EXT, SCHED_OTHER, SCHED_IDLE, and
+ * SCHED_BATCH tasks should use sched_ext.
+ */
+ return 0;
+ }
+
+ void BPF_STRUCT_OPS(simple_exit, struct scx_exit_info *ei)
+ {
+ exit_type = ei->type;
+ }
+
+ SEC(".struct_ops")
+ struct sched_ext_ops simple_ops = {
+ .select_cpu = (void *)simple_select_cpu,
+ .enqueue = (void *)simple_enqueue,
+ .init = (void *)simple_init,
+ .exit = (void *)simple_exit,
+ .name = "simple",
+ };
+
+Dispatch Queues
+---------------
+
+To match the impedance between the scheduler core and the BPF scheduler,
+sched_ext uses DSQs (dispatch queues) which can operate as both a FIFO and a
+priority queue. By default, there is one global FIFO (``SCX_DSQ_GLOBAL``),
+and one local dsq per CPU (``SCX_DSQ_LOCAL``). The BPF scheduler can manage
+an arbitrary number of dsq's using ``scx_bpf_create_dsq()`` and
+``scx_bpf_destroy_dsq()``.
+
+A CPU always executes a task from its local DSQ. A task is "dispatched" to a
+DSQ. A non-local DSQ is "consumed" to transfer a task to the consuming CPU's
+local DSQ.
+
+When a CPU is looking for the next task to run, if the local DSQ is not
+empty, the first task is picked. Otherwise, the CPU tries to consume the
+global DSQ. If that doesn't yield a runnable task either, ``ops.dispatch()``
+is invoked.
+
+Scheduling Cycle
+----------------
+
+The following briefly shows how a waking task is scheduled and executed.
+
+1. When a task is waking up, ``ops.select_cpu()`` is the first operation
+ invoked. This serves two purposes. First, CPU selection optimization
+ hint. Second, waking up the selected CPU if idle.
+
+ The CPU selected by ``ops.select_cpu()`` is an optimization hint and not
+ binding. The actual decision is made at the last step of scheduling.
+ However, there is a small performance gain if the CPU
+ ``ops.select_cpu()`` returns matches the CPU the task eventually runs on.
+
+ A side-effect of selecting a CPU is waking it up from idle. While a BPF
+ scheduler can wake up any cpu using the ``scx_bpf_kick_cpu()`` helper,
+ using ``ops.select_cpu()`` judiciously can be simpler and more efficient.
+
+ A task can be immediately dispatched to a DSQ from ``ops.select_cpu()`` by
+ calling ``scx_bpf_dispatch()``. If the task is dispatched to
+ ``SCX_DSQ_LOCAL`` from ``ops.select_cpu()``, it will be dispatched to the
+ local DSQ of whichever CPU is returned from ``ops.select_cpu()``.
+ Additionally, dispatching directly from ``ops.select_cpu()`` will cause the
+ ``ops.enqueue()`` callback to be skipped.
+
+ Note that the scheduler core will ignore an invalid CPU selection, for
+ example, if it's outside the allowed cpumask of the task.
+
+2. Once the target CPU is selected, ``ops.enqueue()`` is invoked (unless the
+ task was dispatched directly from ``ops.select_cpu()``). ``ops.enqueue()``
+ can make one of the following decisions:
+
+ * Immediately dispatch the task to either the global or local DSQ by
+ calling ``scx_bpf_dispatch()`` with ``SCX_DSQ_GLOBAL`` or
+ ``SCX_DSQ_LOCAL``, respectively.
+
+ * Immediately dispatch the task to a custom DSQ by calling
+ ``scx_bpf_dispatch()`` with a DSQ ID which is smaller than 2^63.
+
+ * Queue the task on the BPF side.
+
+3. When a CPU is ready to schedule, it first looks at its local DSQ. If
+ empty, it then looks at the global DSQ. If there still isn't a task to
+ run, ``ops.dispatch()`` is invoked which can use the following two
+ functions to populate the local DSQ.
+
+ * ``scx_bpf_dispatch()`` dispatches a task to a DSQ. Any target DSQ can
+ be used - ``SCX_DSQ_LOCAL``, ``SCX_DSQ_LOCAL_ON | cpu``,
+ ``SCX_DSQ_GLOBAL`` or a custom DSQ. While ``scx_bpf_dispatch()``
+ currently can't be called with BPF locks held, this is being worked on
+ and will be supported. ``scx_bpf_dispatch()`` schedules dispatching
+ rather than performing them immediately. There can be up to
+ ``ops.dispatch_max_batch`` pending tasks.
+
+ * ``scx_bpf_consume()`` tranfers a task from the specified non-local DSQ
+ to the dispatching DSQ. This function cannot be called with any BPF
+ locks held. ``scx_bpf_consume()`` flushes the pending dispatched tasks
+ before trying to consume the specified DSQ.
+
+4. After ``ops.dispatch()`` returns, if there are tasks in the local DSQ,
+ the CPU runs the first one. If empty, the following steps are taken:
+
+ * Try to consume the global DSQ. If successful, run the task.
+
+ * If ``ops.dispatch()`` has dispatched any tasks, retry #3.
+
+ * If the previous task is an SCX task and still runnable, keep executing
+ it (see ``SCX_OPS_ENQ_LAST``).
+
+ * Go idle.
+
+Note that the BPF scheduler can always choose to dispatch tasks immediately
+in ``ops.enqueue()`` as illustrated in the above simple example. If only the
+built-in DSQs are used, there is no need to implement ``ops.dispatch()`` as
+a task is never queued on the BPF scheduler and both the local and global
+DSQs are consumed automatically.
+
+``scx_bpf_dispatch()`` queues the task on the FIFO of the target DSQ. Use
+``scx_bpf_dispatch_vtime()`` for the priority queue. Internal DSQs such as
+``SCX_DSQ_LOCAL`` and ``SCX_DSQ_GLOBAL`` do not support priority-queue
+dispatching, and must be dispatched to with ``scx_bpf_dispatch()``. See the
+function documentation and usage in ``tools/sched_ext/scx_simple.bpf.c`` for
+more information.
+
+Where to Look
+=============
+
+* ``include/linux/sched/ext.h`` defines the core data structures, ops table
+ and constants.
+
+* ``kernel/sched/ext.c`` contains sched_ext core implementation and helpers.
+ The functions prefixed with ``scx_bpf_`` can be called from the BPF
+ scheduler.
+
+* ``tools/sched_ext/`` hosts example BPF scheduler implementations.
+
+ * ``scx_simple[.bpf].c``: Minimal global FIFO scheduler example using a
+ custom DSQ.
+
+ * ``scx_qmap[.bpf].c``: A multi-level FIFO scheduler supporting five
+ levels of priority implemented with ``BPF_MAP_TYPE_QUEUE``.
+
+ABI Instability
+===============
+
+The APIs provided by sched_ext to BPF schedulers programs have no stability
+guarantees. This includes the ops table callbacks and constants defined in
+``include/linux/sched/ext.h``, as well as the ``scx_bpf_`` kfuncs defined in
+``kernel/sched/ext.c``.
+
+While we will attempt to provide a relatively stable API surface when
+possible, they are subject to change without warning between kernel
+versions.
diff --git a/MAINTAINERS b/MAINTAINERS
index 16df466c205d..3345a15afded 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20353,6 +20353,19 @@ F: include/linux/wait.h
F: include/uapi/linux/sched.h
F: kernel/sched/
+SCHEDULER - SCHED_EXT
+R: Tejun Heo <tj@kernel.org>
+R: David Vernet <void@manifault.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+W: https://github.com/sched-ext/scx
+T: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git
+F: include/linux/sched/ext.h
+F: kernel/sched/ext.h
+F: kernel/sched/ext.c
+F: tools/sched_ext/
+F: tools/testing/selftests/sched_ext
+
SCIOSENSE ENS160 MULTI-GAS SENSOR DRIVER
M: Gustavo Silva <gustavograzs@gmail.com>
S: Maintained
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 14f8f00fdcf9..930b04e3d148 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -531,6 +531,7 @@ static const struct sysrq_key_op *sysrq_key_table[62] = {
NULL, /* P */
NULL, /* Q */
&sysrq_replay_logs_op, /* R */
+ /* S: May be registered by sched_ext for resetting */
NULL, /* S */
NULL, /* T */
NULL, /* U */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1ae44793132a..19ec49a9179b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -133,6 +133,7 @@
*(__dl_sched_class) \
*(__rt_sched_class) \
*(__fair_sched_class) \
+ *(__ext_sched_class) \
*(__idle_sched_class) \
__sched_class_lowest = .;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c60ba0ab1462..7139b33cb104 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -28,8 +28,6 @@
struct kernel_clone_args;
-#ifdef CONFIG_CGROUPS
-
/*
* All weight knobs on the default hierarchy should use the following min,
* default and max values. The default value is the logarithmic center of
@@ -39,6 +37,8 @@ struct kernel_clone_args;
#define CGROUP_WEIGHT_DFL 100
#define CGROUP_WEIGHT_MAX 10000
+#ifdef CONFIG_CGROUPS
+
enum {
CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */
CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1c771ea4481d..c5a7901b2580 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -82,6 +82,8 @@ struct task_group;
struct task_struct;
struct user_event_mm;
+#include <linux/sched/ext.h>
+
/*
* Task state bitmask. NOTE! These bits are also
* encoded in fs/proc/array.c: get_task_state().
@@ -812,6 +814,9 @@ struct task_struct {
struct sched_rt_entity rt;
struct sched_dl_entity dl;
struct sched_dl_entity *dl_server;
+#ifdef CONFIG_SCHED_CLASS_EXT
+ struct sched_ext_entity scx;
+#endif
const struct sched_class *sched_class;
#ifdef CONFIG_SCHED_CORE
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
new file mode 100644
index 000000000000..76166d3b14fc
--- /dev/null
+++ b/include/linux/sched/ext.h
@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
+ *
+ * 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 _LINUX_SCHED_EXT_H
+#define _LINUX_SCHED_EXT_H
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+
+#include <linux/llist.h>
+#include <linux/rhashtable-types.h>
+
+enum scx_public_consts {
+ SCX_OPS_NAME_LEN = 128,
+
+ SCX_SLICE_DFL = 20 * 1000000, /* 20ms */
+ SCX_SLICE_INF = U64_MAX, /* infinite, implies nohz */
+};
+
+/*
+ * DSQ (dispatch queue) IDs are 64bit of the format:
+ *
+ * Bits: [63] [62 .. 0]
+ * [ B] [ ID ]
+ *
+ * B: 1 for IDs for built-in DSQs, 0 for ops-created user DSQs
+ * ID: 63 bit ID
+ *
+ * Built-in IDs:
+ *
+ * Bits: [63] [62] [61..32] [31 .. 0]
+ * [ 1] [ L] [ R ] [ V ]
+ *
+ * 1: 1 for built-in DSQs.
+ * L: 1 for LOCAL_ON DSQ IDs, 0 for others
+ * V: For LOCAL_ON DSQ IDs, a CPU number. For others, a pre-defined value.
+ */
+enum scx_dsq_id_flags {
+ SCX_DSQ_FLAG_BUILTIN = 1LLU << 63,
+ SCX_DSQ_FLAG_LOCAL_ON = 1LLU << 62,
+
+ SCX_DSQ_INVALID = SCX_DSQ_FLAG_BUILTIN | 0,
+ SCX_DSQ_GLOBAL = SCX_DSQ_FLAG_BUILTIN | 1,
+ SCX_DSQ_LOCAL = SCX_DSQ_FLAG_BUILTIN | 2,
+ SCX_DSQ_LOCAL_ON = SCX_DSQ_FLAG_BUILTIN | SCX_DSQ_FLAG_LOCAL_ON,
+ SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU,
+};
+
+/*
+ * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered
+ * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to
+ * buffer between the scheduler core and the BPF scheduler. See the
+ * documentation for more details.
+ */
+struct scx_dispatch_q {
+ raw_spinlock_t lock;
+ struct list_head list; /* tasks in dispatch order */
+ struct rb_root priq; /* used to order by p->scx.dsq_vtime */
+ u32 nr;
+ u32 seq; /* used by BPF iter */
+ u64 id;
+ struct rhash_head hash_node;
+ struct llist_node free_node;
+ struct rcu_head rcu;
+};
+
+/* scx_entity.flags */
+enum scx_ent_flags {
+ SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */
+ SCX_TASK_BAL_KEEP = 1 << 1, /* balance decided to keep current */
+ SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */
+ SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */
+
+ SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */
+ SCX_TASK_STATE_BITS = 2,
+ SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT,
+
+ SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */
+};
+
+/* scx_entity.flags & SCX_TASK_STATE_MASK */
+enum scx_task_state {
+ SCX_TASK_NONE, /* ops.init_task() not called yet */
+ SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */
+ SCX_TASK_READY, /* fully initialized, but not in sched_ext */
+ SCX_TASK_ENABLED, /* fully initialized and in sched_ext */
+
+ SCX_TASK_NR_STATES,
+};
+
+/* scx_entity.dsq_flags */
+enum scx_ent_dsq_flags {
+ SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */
+};
+
+/*
+ * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from
+ * everywhere and the following bits track which kfunc sets are currently
+ * allowed for %current. This simple per-task tracking works because SCX ops
+ * nest in a limited way. BPF will likely implement a way to allow and disallow
+ * kfuncs depending on the calling context which will replace this manual
+ * mechanism. See scx_kf_allow().
+ */
+enum scx_kf_mask {
+ SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */
+ /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */
+ SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */
+ /* ops.dequeue (in REST) may be nested inside DISPATCH */
+ SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */
+ SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */
+ SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */
+ SCX_KF_REST = 1 << 4, /* other rq-locked operations */
+
+ __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH |
+ SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST,
+ __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST,
+};
+
+enum scx_dsq_lnode_flags {
+ SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0,
+
+ /* high 16 bits can be for iter cursor flags */
+ __SCX_DSQ_LNODE_PRIV_SHIFT = 16,
+};
+
+struct scx_dsq_list_node {
+ struct list_head node;
+ u32 flags;
+ u32 priv; /* can be used by iter cursor */
+};
+
+/*
+ * The following is embedded in task_struct and contains all fields necessary
+ * for a task to be scheduled by SCX.
+ */
+struct sched_ext_entity {
+ struct scx_dispatch_q *dsq;
+ struct scx_dsq_list_node dsq_list; /* dispatch order */
+ struct rb_node dsq_priq; /* p->scx.dsq_vtime order */
+ u32 dsq_seq;
+ u32 dsq_flags; /* protected by DSQ lock */
+ u32 flags; /* protected by rq lock */
+ u32 weight;
+ s32 sticky_cpu;
+ s32 holding_cpu;
+ u32 kf_mask; /* see scx_kf_mask above */
+ struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */
+ atomic_long_t ops_state;
+
+ struct list_head runnable_node; /* rq->scx.runnable_list */
+ unsigned long runnable_at;
+
+#ifdef CONFIG_SCHED_CORE
+ u64 core_sched_at; /* see scx_prio_less() */
+#endif
+ u64 ddsp_dsq_id;
+ u64 ddsp_enq_flags;
+
+ /* BPF scheduler modifiable fields */
+
+ /*
+ * Runtime budget in nsecs. This is usually set through
+ * scx_bpf_dispatch() but can also be modified directly by the BPF
+ * scheduler. Automatically decreased by SCX as the task executes. On
+ * depletion, a scheduling event is triggered.
+ *
+ * This value is cleared to zero if the task is preempted by
+ * %SCX_KICK_PREEMPT and shouldn't be used to determine how long the
+ * task ran. Use p->se.sum_exec_runtime instead.
+ */
+ u64 slice;
+
+ /*
+ * Used to order tasks when dispatching to the vtime-ordered priority
+ * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime()
+ * but can also be modified directly by the BPF scheduler. Modifying it
+ * while a task is queued on a dsq may mangle the ordering and is not
+ * recommended.
+ */
+ u64 dsq_vtime;
+
+ /*
+ * If set, reject future sched_setscheduler(2) calls updating the policy
+ * to %SCHED_EXT with -%EACCES.
+ *
+ * Can be set from ops.init_task() while the BPF scheduler is being
+ * loaded (!scx_init_task_args->fork). If set and the task's policy is
+ * already %SCHED_EXT, the task's policy is rejected and forcefully
+ * reverted to %SCHED_NORMAL. The number of such events are reported
+ * through /sys/kernel/debug/sched_ext::nr_rejected. Setting this flag
+ * during fork is not allowed.
+ */
+ bool disallow; /* reject switching into SCX */
+
+ /* cold fields */
+#ifdef CONFIG_EXT_GROUP_SCHED
+ struct cgroup *cgrp_moving_from;
+#endif
+ /* must be the last field, see init_scx_entity() */
+ struct list_head tasks_node;
+};
+
+void sched_ext_free(struct task_struct *p);
+void print_scx_info(const char *log_lvl, struct task_struct *p);
+
+#else /* !CONFIG_SCHED_CLASS_EXT */
+
+static inline void sched_ext_free(struct task_struct *p) {}
+static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+#endif /* _LINUX_SCHED_EXT_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index d362aacf9f89..0f2aeb37bbb0 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -63,7 +63,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
-extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
+extern void sched_cancel_fork(struct task_struct *p);
extern void sched_post_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);
@@ -119,6 +120,11 @@ static inline struct task_struct *get_task_struct(struct task_struct *t)
return t;
}
+static inline struct task_struct *tryget_task_struct(struct task_struct *t)
+{
+ return refcount_inc_not_zero(&t->usage) ? t : NULL;
+}
+
extern void __put_task_struct(struct task_struct *t);
extern void __put_task_struct_rcu_cb(struct rcu_head *rhp);
diff --git a/include/trace/events/sched_ext.h b/include/trace/events/sched_ext.h
new file mode 100644
index 000000000000..fe19da7315a9
--- /dev/null
+++ b/include/trace/events/sched_ext.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched_ext
+
+#if !defined(_TRACE_SCHED_EXT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_EXT_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(sched_ext_dump,
+
+ TP_PROTO(const char *line),
+
+ TP_ARGS(line),
+
+ TP_STRUCT__entry(
+ __string(line, line)
+ ),
+
+ TP_fast_assign(
+ __assign_str(line);
+ ),
+
+ TP_printk("%s",
+ __get_str(line)
+ )
+);
+
+#endif /* _TRACE_SCHED_EXT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 3bac0a8ceab2..359a14cc76a4 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -118,6 +118,7 @@ struct clone_args {
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
#define SCHED_DEADLINE 6
+#define SCHED_EXT 7
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK 0x40000000
diff --git a/init/Kconfig b/init/Kconfig
index 08a0d51afaae..e1a88d48d652 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1028,9 +1028,13 @@ menuconfig CGROUP_SCHED
tasks.
if CGROUP_SCHED
+config GROUP_SCHED_WEIGHT
+ def_bool n
+
config FAIR_GROUP_SCHED
bool "Group scheduling for SCHED_OTHER"
depends on CGROUP_SCHED
+ select GROUP_SCHED_WEIGHT
default CGROUP_SCHED
config CFS_BANDWIDTH
@@ -1055,6 +1059,12 @@ config RT_GROUP_SCHED
realtime bandwidth for them.
See Documentation/scheduler/sched-rt-group.rst for more information.
+config EXT_GROUP_SCHED
+ bool
+ depends on SCHED_CLASS_EXT && CGROUP_SCHED
+ select GROUP_SCHED_WEIGHT
+ default y
+
endif #CGROUP_SCHED
config SCHED_MM_CID
diff --git a/init/init_task.c b/init/init_task.c
index eeb110c65fe2..e222722e790b 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -6,6 +6,7 @@
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
+#include <linux/sched/ext.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
@@ -98,6 +99,17 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
#endif
#ifdef CONFIG_CGROUP_SCHED
.sched_task_group = &root_task_group,
+#endif
+#ifdef CONFIG_SCHED_CLASS_EXT
+ .scx = {
+ .dsq_list.node = LIST_HEAD_INIT(init_task.scx.dsq_list.node),
+ .sticky_cpu = -1,
+ .holding_cpu = -1,
+ .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node),
+ .runnable_at = INITIAL_JIFFIES,
+ .ddsp_dsq_id = SCX_DSQ_INVALID,
+ .slice = SCX_SLICE_DFL,
+ },
#endif
.ptraced = LIST_HEAD_INIT(init_task.ptraced),
.ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry),
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index c2f1fd95a821..fe782cd77388 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -133,4 +133,29 @@ config SCHED_CORE
which is the likely usage by Linux distributions, there should
be no measurable impact on performance.
-
+config SCHED_CLASS_EXT
+ bool "Extensible Scheduling Class"
+ depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF
+ select STACKTRACE if STACKTRACE_SUPPORT
+ help
+ This option enables a new scheduler class sched_ext (SCX), which
+ allows scheduling policies to be implemented as BPF programs to
+ achieve the following:
+
+ - Ease of experimentation and exploration: Enabling rapid
+ iteration of new scheduling policies.
+ - Customization: Building application-specific schedulers which
+ implement policies that are not applicable to general-purpose
+ schedulers.
+ - Rapid scheduler deployments: Non-disruptive swap outs of
+ scheduling policies in production environments.
+
+ sched_ext leverages BPF struct_ops feature to define a structure
+ which exports function callbacks and flags to BPF programs that
+ wish to implement scheduling policies. The struct_ops structure
+ exported by sched_ext is struct sched_ext_ops, and is conceptually
+ similar to struct sched_class.
+
+ For more information:
+ Documentation/scheduler/sched-ext.rst
+ https://github.com/sched-ext/scx
diff --git a/kernel/fork.c b/kernel/fork.c
index 003de4829c15..eb290420d926 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -23,6 +23,7 @@
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
+#include <linux/sched/ext.h>
#include <linux/seq_file.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
@@ -973,6 +974,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(refcount_read(&tsk->usage));
WARN_ON(tsk == current);
+ sched_ext_free(tsk);
io_uring_free(tsk);
cgroup_free(tsk);
task_numa_free(tsk, true);
@@ -2352,7 +2354,7 @@ __latent_entropy struct task_struct *copy_process(
retval = perf_event_init_task(p, clone_flags);
if (retval)
- goto bad_fork_cleanup_policy;
+ goto bad_fork_sched_cancel_fork;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_perf;
@@ -2485,7 +2487,9 @@ __latent_entropy struct task_struct *copy_process(
* cgroup specific, it unconditionally needs to place the task on a
* runqueue.
*/
- sched_cgroup_fork(p, args);
+ retval = sched_cgroup_fork(p, args);
+ if (retval)
+ goto bad_fork_cancel_cgroup;
/*
* From this point on we must avoid any synchronous user-space
@@ -2531,13 +2535,13 @@ __latent_entropy struct task_struct *copy_process(
/* Don't start children in a dying pid namespace */
if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
retval = -ENOMEM;
- goto bad_fork_cancel_cgroup;
+ goto bad_fork_core_free;
}
/* Let kill terminate clone/fork in the middle */
if (fatal_signal_pending(current)) {
retval = -EINTR;
- goto bad_fork_cancel_cgroup;
+ goto bad_fork_core_free;
}
/* No more failure paths after this point. */
@@ -2611,10 +2615,11 @@ __latent_entropy struct task_struct *copy_process(
return p;
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
sched_core_free(p);
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
+bad_fork_cancel_cgroup:
cgroup_cancel_fork(p, args);
bad_fork_put_pidfd:
if (clone_flags & CLONE_PIDFD) {
@@ -2653,6 +2658,8 @@ __latent_entropy struct task_struct *copy_process(
audit_free(p);
bad_fork_cleanup_perf:
perf_event_free_task(p);
+bad_fork_sched_cancel_fork:
+ sched_cancel_fork(p);
bad_fork_cleanup_policy:
lockdep_free_task(p);
#ifdef CONFIG_NUMA
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index 39c315182b35..fae1f5c921eb 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -16,18 +16,25 @@
#include <linux/sched/clock.h>
#include <linux/sched/cputime.h>
#include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
#include <linux/sched/posix-timers.h>
#include <linux/sched/rt.h>
#include <linux/cpuidle.h>
#include <linux/jiffies.h>
+#include <linux/kobject.h>
#include <linux/livepatch.h>
+#include <linux/pm.h>
#include <linux/psi.h>
+#include <linux/rhashtable.h>
+#include <linux/seq_buf.h>
#include <linux/seqlock_api.h>
#include <linux/slab.h>
#include <linux/suspend.h>
#include <linux/tsacct_kern.h>
#include <linux/vtime.h>
+#include <linux/sysrq.h>
+#include <linux/percpu-rwsem.h>
#include <uapi/linux/sched/types.h>
@@ -52,4 +59,8 @@
#include "cputime.c"
#include "deadline.c"
+#ifdef CONFIG_SCHED_CLASS_EXT
+# include "ext.c"
+#endif
+
#include "syscalls.c"
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1af59cf714cd..8ae04bd4a5a4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -169,7 +169,10 @@ static inline int __task_prio(const struct task_struct *p)
if (p->sched_class == &idle_sched_class)
return MAX_RT_PRIO + NICE_WIDTH; /* 140 */
- return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */
+ if (task_on_scx(p))
+ return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */
+
+ return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */
}
/*
@@ -198,6 +201,11 @@ static inline bool prio_less(const struct task_struct *a,
if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */
return cfs_prio_less(a, b, in_fi);
+#ifdef CONFIG_SCHED_CLASS_EXT
+ if (pa == MAX_RT_PRIO + MAX_NICE + 1) /* ext */
+ return scx_prio_less(a, b, in_fi);
+#endif
+
return false;
}
@@ -1255,11 +1263,14 @@ bool sched_can_stop_tick(struct rq *rq)
return true;
/*
- * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left;
- * if there's more than one we need the tick for involuntary
- * preemption.
+ * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks
+ * left. For CFS, if there's more than one we need the tick for
+ * involuntary preemption. For SCX, ask.
*/
- if (rq->nr_running > 1)
+ if (scx_enabled() && !scx_can_stop_tick(rq))
+ return false;
+
+ if (rq->cfs.nr_running > 1)
return false;
/*
@@ -1341,8 +1352,8 @@ void set_load_weight(struct task_struct *p, bool update_load)
* SCHED_OTHER tasks have to update their load when changing their
* weight
*/
- if (update_load && p->sched_class == &fair_sched_class)
- reweight_task(p, &lw);
+ if (update_load && p->sched_class->reweight_task)
+ p->sched_class->reweight_task(task_rq(p), p, &lw);
else
p->se.load = lw;
}
@@ -2031,6 +2042,17 @@ inline int task_curr(const struct task_struct *p)
return cpu_curr(task_cpu(p)) == p;
}
+/*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+ const struct sched_class *prev_class)
+{
+ if (prev_class != p->sched_class && p->sched_class->switching_to)
+ p->sched_class->switching_to(rq, p);
+}
+
/*
* switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
* use the balance_callback list if you want balancing.
@@ -2289,7 +2311,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
{
/* When not in the task's cpumask, no point in looking further. */
- if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+ if (!task_allowed_on_cpu(p, cpu))
return false;
/* migrate_disabled() must be allowed to finish. */
@@ -2298,7 +2320,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
/* Non kernel threads are not allowed during either online or offline. */
if (!(p->flags & PF_KTHREAD))
- return cpu_active(cpu) && task_cpu_possible(cpu, p);
+ return cpu_active(cpu);
/* KTHREAD_IS_PER_CPU is always allowed. */
if (kthread_is_per_cpu(p))
@@ -3775,6 +3797,15 @@ bool cpus_share_resources(int this_cpu, int that_cpu)
static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
{
+ /*
+ * The BPF scheduler may depend on select_task_rq() being invoked during
+ * wakeups. In addition, @p may end up executing on a different CPU
+ * regardless of what happens in the wakeup path making the ttwu_queue
+ * optimization less meaningful. Skip if on SCX.
+ */
+ if (task_on_scx(p))
+ return false;
+
/*
* Do not complicate things with the async wake_list while the CPU is
* in hotplug state.
@@ -4342,6 +4373,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->rt.on_rq = 0;
p->rt.on_list = 0;
+#ifdef CONFIG_SCHED_CLASS_EXT
+ init_scx_entity(&p->scx);
+#endif
+
#ifdef CONFIG_PREEMPT_NOTIFIERS
INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif
@@ -4582,10 +4617,18 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
if (dl_prio(p->prio))
return -EAGAIN;
- else if (rt_prio(p->prio))
+
+ scx_pre_fork(p);
+
+ if (rt_prio(p->prio)) {
p->sched_class = &rt_sched_class;
- else
+#ifdef CONFIG_SCHED_CLASS_EXT
+ } else if (task_should_scx(p)) {
+ p->sched_class = &ext_sched_class;
+#endif
+ } else {
p->sched_class = &fair_sched_class;
+ }
init_entity_runnable_average(&p->se);
@@ -4605,7 +4648,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
return 0;
}
-void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
{
unsigned long flags;
@@ -4632,11 +4675,19 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+ return scx_fork(p);
+}
+
+void sched_cancel_fork(struct task_struct *p)
+{
+ scx_cancel_fork(p);
}
void sched_post_fork(struct task_struct *p)
{
uclamp_post_fork(p);
+ scx_post_fork(p);
}
unsigned long to_ratio(u64 period, u64 runtime)
@@ -5469,6 +5520,7 @@ void sched_tick(void)
calc_global_load_tick(rq);
sched_core_tick(rq);
task_tick_mm_cid(rq, curr);
+ scx_tick(rq);
rq_unlock(rq, &rf);
@@ -5481,8 +5533,10 @@ void sched_tick(void)
wq_worker_tick(curr);
#ifdef CONFIG_SMP
- rq->idle_balance = idle_cpu(cpu);
- sched_balance_trigger(rq);
+ if (!scx_switched_all()) {
+ rq->idle_balance = idle_cpu(cpu);
+ sched_balance_trigger(rq);
+ }
#endif
}
@@ -5772,8 +5826,19 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
struct rq_flags *rf)
{
-#ifdef CONFIG_SMP
+ const struct sched_class *start_class = prev->sched_class;
const struct sched_class *class;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+ /*
+ * SCX requires a balance() call before every pick_next_task() including
+ * when waking up from SCHED_IDLE. If @start_class is below SCX, start
+ * from SCX instead.
+ */
+ if (scx_enabled() && sched_class_above(&ext_sched_class, start_class))
+ start_class = &ext_sched_class;
+#endif
+
/*
* We must do the balancing pass before put_prev_task(), such
* that when we release the rq->lock the task is in the same
@@ -5782,11 +5847,10 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
* We can terminate the balance pass as soon as we know there is
* a runnable task of @class priority or higher.
*/
- for_class_range(class, prev->sched_class, &idle_sched_class) {
- if (class->balance(rq, prev, rf))
+ for_active_class_range(class, start_class, &idle_sched_class) {
+ if (class->balance && class->balance(rq, prev, rf))
break;
}
-#endif
put_prev_task(rq, prev);
@@ -5808,6 +5872,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
const struct sched_class *class;
struct task_struct *p;
+ if (scx_enabled())
+ goto restart;
+
/*
* Optimization: we know that if all tasks are in the fair class we can
* call that function directly, but only if the @prev task wasn't of a
@@ -5847,10 +5914,15 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
restart:
put_prev_task_balance(rq, prev, rf);
- for_each_class(class) {
+ for_each_active_class(class) {
p = class->pick_next_task(rq);
- if (p)
+ if (p) {
+ const struct sched_class *prev_class = prev->sched_class;
+
+ if (class != prev_class && prev_class->switch_class)
+ prev_class->switch_class(rq, p);
return p;
+ }
}
BUG(); /* The idle class should always have a runnable task. */
@@ -5880,7 +5952,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
const struct sched_class *class;
struct task_struct *p;
- for_each_class(class) {
+ for_each_active_class(class) {
p = class->pick_task(rq);
if (p)
return p;
@@ -6877,6 +6949,10 @@ void __setscheduler_prio(struct task_struct *p, int prio)
p->sched_class = &dl_sched_class;
else if (rt_prio(prio))
p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_CLASS_EXT
+ else if (task_should_scx(p))
+ p->sched_class = &ext_sched_class;
+#endif
else
p->sched_class = &fair_sched_class;
@@ -7022,6 +7098,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
}
__setscheduler_prio(p, prio);
+ check_class_changing(rq, p, prev_class);
if (queued)
enqueue_task(rq, p, queue_flag);
@@ -7436,6 +7513,7 @@ void sched_show_task(struct task_struct *p)
print_worker_info(KERN_INFO, p);
print_stop_info(KERN_INFO, p);
+ print_scx_info(KERN_INFO, p);
show_stack(p, NULL, KERN_INFO);
put_task_stack(p);
}
@@ -7964,6 +8042,8 @@ int sched_cpu_activate(unsigned int cpu)
cpuset_cpu_active();
}
+ scx_rq_activate(rq);
+
/*
* Put the rq online, if not already. This happens:
*
@@ -8013,6 +8093,8 @@ int sched_cpu_deactivate(unsigned int cpu)
sched_set_rq_offline(rq, cpu);
+ scx_rq_deactivate(rq);
+
/*
* When going down, decrement the number of cores with SMT present.
*/
@@ -8197,11 +8279,15 @@ void __init sched_init(void)
int i;
/* Make sure the linker didn't screw up */
- BUG_ON(&idle_sched_class != &fair_sched_class + 1 ||
- &fair_sched_class != &rt_sched_class + 1 ||
- &rt_sched_class != &dl_sched_class + 1);
#ifdef CONFIG_SMP
- BUG_ON(&dl_sched_class != &stop_sched_class + 1);
+ BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
+#endif
+ BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
+ BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
+ BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
+#ifdef CONFIG_SCHED_CLASS_EXT
+ BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class));
+ BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class));
#endif
wait_bit_init();
@@ -8225,6 +8311,9 @@ void __init sched_init(void)
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
+#ifdef CONFIG_EXT_GROUP_SCHED
+ root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+#endif /* CONFIG_EXT_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
@@ -8370,6 +8459,7 @@ void __init sched_init(void)
balance_push_set(smp_processor_id(), false);
#endif
init_sched_fair_class();
+ init_sched_ext_class();
psi_init();
@@ -8655,6 +8745,7 @@ struct task_group *sched_create_group(struct task_group *parent)
if (!alloc_rt_sched_group(tg, parent))
goto err;
+ scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
alloc_uclamp_sched_group(tg, parent);
return tg;
@@ -8782,6 +8873,7 @@ void sched_move_task(struct task_struct *tsk)
put_prev_task(rq, tsk);
sched_change_group(tsk, group);
+ scx_move_task(tsk);
if (queued)
enqueue_task(rq, tsk, queue_flags);
@@ -8796,11 +8888,6 @@ void sched_move_task(struct task_struct *tsk)
}
}
-static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-{
- return css ? container_of(css, struct task_group, css) : NULL;
-}
-
static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
@@ -8824,6 +8911,11 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
struct task_group *parent = css_tg(css->parent);
+ int ret;
+
+ ret = scx_tg_online(tg);
+ if (ret)
+ return ret;
if (parent)
sched_online_group(tg, parent);
@@ -8838,6 +8930,13 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
return 0;
}
+static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+
+ scx_tg_offline(tg);
+}
+
static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
@@ -8855,9 +8954,9 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
sched_unregister_group(tg);
}
-#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
+#ifdef CONFIG_RT_GROUP_SCHED
struct task_struct *task;
struct cgroup_subsys_state *css;
@@ -8865,9 +8964,9 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
}
- return 0;
-}
#endif
+ return scx_cgroup_can_attach(tset);
+}
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
@@ -8876,6 +8975,13 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
cgroup_taskset_for_each(task, css, tset)
sched_move_task(task);
+
+ scx_cgroup_finish_attach();
+}
+
+static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset)
+{
+ scx_cgroup_cancel_attach(tset);
}
#ifdef CONFIG_UCLAMP_TASK_GROUP
@@ -9052,22 +9158,36 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
}
#endif /* CONFIG_UCLAMP_TASK_GROUP */
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
+static unsigned long tg_weight(struct task_group *tg)
+{
#ifdef CONFIG_FAIR_GROUP_SCHED
+ return scale_load_down(tg->shares);
+#else
+ return sched_weight_from_cgroup(tg->scx_weight);
+#endif
+}
+
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
+ int ret;
+
if (shareval > scale_load_down(ULONG_MAX))
shareval = MAX_SHARES;
- return sched_group_set_shares(css_tg(css), scale_load(shareval));
+ ret = sched_group_set_shares(css_tg(css), scale_load(shareval));
+ if (!ret)
+ scx_group_set_weight(css_tg(css),
+ sched_weight_to_cgroup(shareval));
+ return ret;
}
static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
- struct task_group *tg = css_tg(css);
-
- return (u64) scale_load_down(tg->shares);
+ return tg_weight(css_tg(css));
}
+#endif /* CONFIG_GROUP_SCHED_WEIGHT */
#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);
@@ -9413,7 +9533,6 @@ static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
-#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
@@ -9441,7 +9560,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
}
#endif /* CONFIG_RT_GROUP_SCHED */
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -9451,12 +9570,17 @@ static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 idle)
{
- return sched_group_set_idle(css_tg(css), idle);
+ int ret;
+
+ ret = sched_group_set_idle(css_tg(css), idle);
+ if (!ret)
+ scx_group_set_idle(css_tg(css), idle);
+ return ret;
}
#endif
static struct cftype cpu_legacy_files[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
{
.name = "shares",
.read_u64 = cpu_shares_read_u64,
@@ -9566,38 +9690,35 @@ static int cpu_local_stat_show(struct seq_file *sf,
return 0;
}
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
+
static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
- struct task_group *tg = css_tg(css);
- u64 weight = scale_load_down(tg->shares);
-
- return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024);
+ return sched_weight_to_cgroup(tg_weight(css_tg(css)));
}
static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
- struct cftype *cft, u64 weight)
+ struct cftype *cft, u64 cgrp_weight)
{
- /*
- * cgroup weight knobs should use the common MIN, DFL and MAX
- * values which are 1, 100 and 10000 respectively. While it loses
- * a bit of range on both ends, it maps pretty well onto the shares
- * value used by scheduler and the round-trip conversions preserve
- * the original value over the entire range.
- */
- if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX)
+ unsigned long weight;
+ int ret;
+
+ if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
return -ERANGE;
- weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL);
+ weight = sched_weight_from_cgroup(cgrp_weight);
- return sched_group_set_shares(css_tg(css), scale_load(weight));
+ ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+ if (!ret)
+ scx_group_set_weight(css_tg(css), cgrp_weight);
+ return ret;
}
static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
- unsigned long weight = scale_load_down(css_tg(css)->shares);
+ unsigned long weight = tg_weight(css_tg(css));
int last_delta = INT_MAX;
int prio, delta;
@@ -9616,7 +9737,7 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 nice)
{
unsigned long weight;
- int idx;
+ int idx, ret;
if (nice < MIN_NICE || nice > MAX_NICE)
return -ERANGE;
@@ -9625,9 +9746,13 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
idx = array_index_nospec(idx, 40);
weight = sched_prio_to_weight[idx];
- return sched_group_set_shares(css_tg(css), scale_load(weight));
+ ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+ if (!ret)
+ scx_group_set_weight(css_tg(css),
+ sched_weight_to_cgroup(weight));
+ return ret;
}
-#endif
+#endif /* CONFIG_GROUP_SCHED_WEIGHT */
static void __maybe_unused cpu_period_quota_print(struct seq_file *sf,
long period, long quota)
@@ -9687,7 +9812,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
#endif
static struct cftype cpu_files[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
{
.name = "weight",
.flags = CFTYPE_NOT_ON_ROOT,
@@ -9741,14 +9866,14 @@ static struct cftype cpu_files[] = {
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_online = cpu_cgroup_css_online,
+ .css_offline = cpu_cgroup_css_offline,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
.css_local_stat_show = cpu_local_stat_show,
-#ifdef CONFIG_RT_GROUP_SCHED
.can_attach = cpu_cgroup_can_attach,
-#endif
.attach = cpu_cgroup_attach,
+ .cancel_attach = cpu_cgroup_cancel_attach,
.legacy_cftypes = cpu_legacy_files,
.dfl_cftypes = cpu_files,
.early_init = true,
@@ -10338,3 +10463,38 @@ void sched_mm_cid_fork(struct task_struct *t)
t->mm_cid_active = 1;
}
#endif
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
+ struct sched_enq_and_set_ctx *ctx)
+{
+ struct rq *rq = task_rq(p);
+
+ lockdep_assert_rq_held(rq);
+
+ *ctx = (struct sched_enq_and_set_ctx){
+ .p = p,
+ .queue_flags = queue_flags,
+ .queued = task_on_rq_queued(p),
+ .running = task_current(rq, p),
+ };
+
+ update_rq_clock(rq);
+ if (ctx->queued)
+ dequeue_task(rq, p, queue_flags | DEQUEUE_NOCLOCK);
+ if (ctx->running)
+ put_prev_task(rq, p);
+}
+
+void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx)
+{
+ struct rq *rq = task_rq(ctx->p);
+
+ lockdep_assert_rq_held(rq);
+
+ if (ctx->queued)
+ enqueue_task(rq, ctx->p, ctx->queue_flags | ENQUEUE_NOCLOCK);
+ if (ctx->running)
+ set_next_task(rq, ctx->p);
+}
+#endif /* CONFIG_SCHED_CLASS_EXT */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index eece6244f9d2..e683e5d08daa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -197,8 +197,10 @@ unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
{
- unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+ unsigned long min, max, util = scx_cpuperf_target(sg_cpu->cpu);
+ if (!scx_switched_all())
+ util += cpu_util_cfs_boost(sg_cpu->cpu);
util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
util = max(util, boost);
sg_cpu->bw_min = min;
@@ -325,16 +327,35 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
}
#ifdef CONFIG_NO_HZ_COMMON
-static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+static bool sugov_hold_freq(struct sugov_cpu *sg_cpu)
{
- unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
- bool ret = idle_calls == sg_cpu->saved_idle_calls;
+ unsigned long idle_calls;
+ bool ret;
+
+ /*
+ * The heuristics in this function is for the fair class. For SCX, the
+ * performance target comes directly from the BPF scheduler. Let's just
+ * follow it.
+ */
+ if (scx_switched_all())
+ return false;
+
+ /* if capped by uclamp_max, always update to be in compliance */
+ if (uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)))
+ return false;
+
+ /*
+ * Maintain the frequency if the CPU has not been idle recently, as
+ * reduction is likely to be premature.
+ */
+ idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
+ ret = idle_calls == sg_cpu->saved_idle_calls;
sg_cpu->saved_idle_calls = idle_calls;
return ret;
}
#else
-static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+static inline bool sugov_hold_freq(struct sugov_cpu *sg_cpu) { return false; }
#endif /* CONFIG_NO_HZ_COMMON */
/*
@@ -382,14 +403,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
return;
next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap);
- /*
- * Do not reduce the frequency if the CPU has not been idle
- * recently, as the reduction is likely to be premature then.
- *
- * Except when the rq is capped by uclamp_max.
- */
- if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
- sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+
+ if (sugov_hold_freq(sg_cpu) && next_f < sg_policy->next_freq &&
!sg_policy->need_freq_update) {
next_f = sg_policy->next_freq;
@@ -436,14 +451,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
return;
- /*
- * Do not reduce the target performance level if the CPU has not been
- * idle recently, as the reduction is likely to be premature then.
- *
- * Except when the rq is capped by uclamp_max.
- */
- if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
- sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
+ if (sugov_hold_freq(sg_cpu) && sg_cpu->util < prev_util)
sg_cpu->util = prev_util;
cpufreq_driver_adjust_perf(sg_cpu->cpu, sg_cpu->bw_min,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index c1eb9a1afd13..c057ef46c5f8 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1090,6 +1090,9 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
P(dl.runtime);
P(dl.deadline);
}
+#ifdef CONFIG_SCHED_CLASS_EXT
+ __PS("ext.enabled", task_on_scx(p));
+#endif
#undef PN_SCHEDSTAT
#undef P_SCHEDSTAT
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
new file mode 100644
index 000000000000..5fae2292ec29
--- /dev/null
+++ b/kernel/sched/ext.c
@@ -0,0 +1,7281 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#define SCX_OP_IDX(op) (offsetof(struct sched_ext_ops, op) / sizeof(void (*)(void)))
+
+enum scx_consts {
+ SCX_DSP_DFL_MAX_BATCH = 32,
+ SCX_DSP_MAX_LOOPS = 32,
+ SCX_WATCHDOG_MAX_TIMEOUT = 30 * HZ,
+
+ SCX_EXIT_BT_LEN = 64,
+ SCX_EXIT_MSG_LEN = 1024,
+ SCX_EXIT_DUMP_DFL_LEN = 32768,
+
+ SCX_CPUPERF_ONE = SCHED_CAPACITY_SCALE,
+
+ /*
+ * Iterating all tasks may take a while. Periodically drop
+ * scx_tasks_lock to avoid causing e.g. CSD and RCU stalls.
+ */
+ SCX_OPS_TASK_ITER_BATCH = 32,
+};
+
+enum scx_exit_kind {
+ SCX_EXIT_NONE,
+ SCX_EXIT_DONE,
+
+ SCX_EXIT_UNREG = 64, /* user-space initiated unregistration */
+ SCX_EXIT_UNREG_BPF, /* BPF-initiated unregistration */
+ SCX_EXIT_UNREG_KERN, /* kernel-initiated unregistration */
+ SCX_EXIT_SYSRQ, /* requested by 'S' sysrq */
+
+ SCX_EXIT_ERROR = 1024, /* runtime error, error msg contains details */
+ SCX_EXIT_ERROR_BPF, /* ERROR but triggered through scx_bpf_error() */
+ SCX_EXIT_ERROR_STALL, /* watchdog detected stalled runnable tasks */
+};
+
+/*
+ * An exit code can be specified when exiting with scx_bpf_exit() or
+ * scx_ops_exit(), corresponding to exit_kind UNREG_BPF and UNREG_KERN
+ * respectively. The codes are 64bit of the format:
+ *
+ * Bits: [63 .. 48 47 .. 32 31 .. 0]
+ * [ SYS ACT ] [ SYS RSN ] [ USR ]
+ *
+ * SYS ACT: System-defined exit actions
+ * SYS RSN: System-defined exit reasons
+ * USR : User-defined exit codes and reasons
+ *
+ * Using the above, users may communicate intention and context by ORing system
+ * actions and/or system reasons with a user-defined exit code.
+ */
+enum scx_exit_code {
+ /* Reasons */
+ SCX_ECODE_RSN_HOTPLUG = 1LLU << 32,
+
+ /* Actions */
+ SCX_ECODE_ACT_RESTART = 1LLU << 48,
+};
+
+/*
+ * scx_exit_info is passed to ops.exit() to describe why the BPF scheduler is
+ * being disabled.
+ */
+struct scx_exit_info {
+ /* %SCX_EXIT_* - broad category of the exit reason */
+ enum scx_exit_kind kind;
+
+ /* exit code if gracefully exiting */
+ s64 exit_code;
+
+ /* textual representation of the above */
+ const char *reason;
+
+ /* backtrace if exiting due to an error */
+ unsigned long *bt;
+ u32 bt_len;
+
+ /* informational message */
+ char *msg;
+
+ /* debug dump */
+ char *dump;
+};
+
+/* sched_ext_ops.flags */
+enum scx_ops_flags {
+ /*
+ * Keep built-in idle tracking even if ops.update_idle() is implemented.
+ */
+ SCX_OPS_KEEP_BUILTIN_IDLE = 1LLU << 0,
+
+ /*
+ * By default, if there are no other task to run on the CPU, ext core
+ * keeps running the current task even after its slice expires. If this
+ * flag is specified, such tasks are passed to ops.enqueue() with
+ * %SCX_ENQ_LAST. See the comment above %SCX_ENQ_LAST for more info.
+ */
+ SCX_OPS_ENQ_LAST = 1LLU << 1,
+
+ /*
+ * An exiting task may schedule after PF_EXITING is set. In such cases,
+ * bpf_task_from_pid() may not be able to find the task and if the BPF
+ * scheduler depends on pid lookup for dispatching, the task will be
+ * lost leading to various issues including RCU grace period stalls.
+ *
+ * To mask this problem, by default, unhashed tasks are automatically
+ * dispatched to the local DSQ on enqueue. If the BPF scheduler doesn't
+ * depend on pid lookups and wants to handle these tasks directly, the
+ * following flag can be used.
+ */
+ SCX_OPS_ENQ_EXITING = 1LLU << 2,
+
+ /*
+ * If set, only tasks with policy set to SCHED_EXT are attached to
+ * sched_ext. If clear, SCHED_NORMAL tasks are also included.
+ */
+ SCX_OPS_SWITCH_PARTIAL = 1LLU << 3,
+
+ /*
+ * CPU cgroup support flags
+ */
+ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */
+
+ SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
+ SCX_OPS_ENQ_LAST |
+ SCX_OPS_ENQ_EXITING |
+ SCX_OPS_SWITCH_PARTIAL |
+ SCX_OPS_HAS_CGROUP_WEIGHT,
+};
+
+/* argument container for ops.init_task() */
+struct scx_init_task_args {
+ /*
+ * Set if ops.init_task() is being invoked on the fork path, as opposed
+ * to the scheduler transition path.
+ */
+ bool fork;
+#ifdef CONFIG_EXT_GROUP_SCHED
+ /* the cgroup the task is joining */
+ struct cgroup *cgroup;
+#endif
+};
+
+/* argument container for ops.exit_task() */
+struct scx_exit_task_args {
+ /* Whether the task exited before running on sched_ext. */
+ bool cancelled;
+};
+
+/* argument container for ops->cgroup_init() */
+struct scx_cgroup_init_args {
+ /* the weight of the cgroup [1..10000] */
+ u32 weight;
+};
+
+enum scx_cpu_preempt_reason {
+ /* next task is being scheduled by &sched_class_rt */
+ SCX_CPU_PREEMPT_RT,
+ /* next task is being scheduled by &sched_class_dl */
+ SCX_CPU_PREEMPT_DL,
+ /* next task is being scheduled by &sched_class_stop */
+ SCX_CPU_PREEMPT_STOP,
+ /* unknown reason for SCX being preempted */
+ SCX_CPU_PREEMPT_UNKNOWN,
+};
+
+/*
+ * Argument container for ops->cpu_acquire(). Currently empty, but may be
+ * expanded in the future.
+ */
+struct scx_cpu_acquire_args {};
+
+/* argument container for ops->cpu_release() */
+struct scx_cpu_release_args {
+ /* the reason the CPU was preempted */
+ enum scx_cpu_preempt_reason reason;
+
+ /* the task that's going to be scheduled on the CPU */
+ struct task_struct *task;
+};
+
+/*
+ * Informational context provided to dump operations.
+ */
+struct scx_dump_ctx {
+ enum scx_exit_kind kind;
+ s64 exit_code;
+ const char *reason;
+ u64 at_ns;
+ u64 at_jiffies;
+};
+
+/**
+ * struct sched_ext_ops - Operation table for BPF scheduler implementation
+ *
+ * Userland can implement an arbitrary scheduling policy by implementing and
+ * loading operations in this table.
+ */
+struct sched_ext_ops {
+ /**
+ * select_cpu - Pick the target CPU for a task which is being woken up
+ * @p: task being woken up
+ * @prev_cpu: the cpu @p was on before sleeping
+ * @wake_flags: SCX_WAKE_*
+ *
+ * Decision made here isn't final. @p may be moved to any CPU while it
+ * is getting dispatched for execution later. However, as @p is not on
+ * the rq at this point, getting the eventual execution CPU right here
+ * saves a small bit of overhead down the line.
+ *
+ * If an idle CPU is returned, the CPU is kicked and will try to
+ * dispatch. While an explicit custom mechanism can be added,
+ * select_cpu() serves as the default way to wake up idle CPUs.
+ *
+ * @p may be dispatched directly by calling scx_bpf_dispatch(). If @p
+ * is dispatched, the ops.enqueue() callback will be skipped. Finally,
+ * if @p is dispatched to SCX_DSQ_LOCAL, it will be dispatched to the
+ * local DSQ of whatever CPU is returned by this callback.
+ */
+ s32 (*select_cpu)(struct task_struct *p, s32 prev_cpu, u64 wake_flags);
+
+ /**
+ * enqueue - Enqueue a task on the BPF scheduler
+ * @p: task being enqueued
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * @p is ready to run. Dispatch directly by calling scx_bpf_dispatch()
+ * or enqueue on the BPF scheduler. If not directly dispatched, the bpf
+ * scheduler owns @p and if it fails to dispatch @p, the task will
+ * stall.
+ *
+ * If @p was dispatched from ops.select_cpu(), this callback is
+ * skipped.
+ */
+ void (*enqueue)(struct task_struct *p, u64 enq_flags);
+
+ /**
+ * dequeue - Remove a task from the BPF scheduler
+ * @p: task being dequeued
+ * @deq_flags: %SCX_DEQ_*
+ *
+ * Remove @p from the BPF scheduler. This is usually called to isolate
+ * the task while updating its scheduling properties (e.g. priority).
+ *
+ * The ext core keeps track of whether the BPF side owns a given task or
+ * not and can gracefully ignore spurious dispatches from BPF side,
+ * which makes it safe to not implement this method. However, depending
+ * on the scheduling logic, this can lead to confusing behaviors - e.g.
+ * scheduling position not being updated across a priority change.
+ */
+ void (*dequeue)(struct task_struct *p, u64 deq_flags);
+
+ /**
+ * dispatch - Dispatch tasks from the BPF scheduler and/or consume DSQs
+ * @cpu: CPU to dispatch tasks for
+ * @prev: previous task being switched out
+ *
+ * Called when a CPU's local dsq is empty. The operation should dispatch
+ * one or more tasks from the BPF scheduler into the DSQs using
+ * scx_bpf_dispatch() and/or consume user DSQs into the local DSQ using
+ * scx_bpf_consume().
+ *
+ * The maximum number of times scx_bpf_dispatch() can be called without
+ * an intervening scx_bpf_consume() is specified by
+ * ops.dispatch_max_batch. See the comments on top of the two functions
+ * for more details.
+ *
+ * When not %NULL, @prev is an SCX task with its slice depleted. If
+ * @prev is still runnable as indicated by set %SCX_TASK_QUEUED in
+ * @prev->scx.flags, it is not enqueued yet and will be enqueued after
+ * ops.dispatch() returns. To keep executing @prev, return without
+ * dispatching or consuming any tasks. Also see %SCX_OPS_ENQ_LAST.
+ */
+ void (*dispatch)(s32 cpu, struct task_struct *prev);
+
+ /**
+ * tick - Periodic tick
+ * @p: task running currently
+ *
+ * This operation is called every 1/HZ seconds on CPUs which are
+ * executing an SCX task. Setting @p->scx.slice to 0 will trigger an
+ * immediate dispatch cycle on the CPU.
+ */
+ void (*tick)(struct task_struct *p);
+
+ /**
+ * runnable - A task is becoming runnable on its associated CPU
+ * @p: task becoming runnable
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * This and the following three functions can be used to track a task's
+ * execution state transitions. A task becomes ->runnable() on a CPU,
+ * and then goes through one or more ->running() and ->stopping() pairs
+ * as it runs on the CPU, and eventually becomes ->quiescent() when it's
+ * done running on the CPU.
+ *
+ * @p is becoming runnable on the CPU because it's
+ *
+ * - waking up (%SCX_ENQ_WAKEUP)
+ * - being moved from another CPU
+ * - being restored after temporarily taken off the queue for an
+ * attribute change.
+ *
+ * This and ->enqueue() are related but not coupled. This operation
+ * notifies @p's state transition and may not be followed by ->enqueue()
+ * e.g. when @p is being dispatched to a remote CPU, or when @p is
+ * being enqueued on a CPU experiencing a hotplug event. Likewise, a
+ * task may be ->enqueue()'d without being preceded by this operation
+ * e.g. after exhausting its slice.
+ */
+ void (*runnable)(struct task_struct *p, u64 enq_flags);
+
+ /**
+ * running - A task is starting to run on its associated CPU
+ * @p: task starting to run
+ *
+ * See ->runnable() for explanation on the task state notifiers.
+ */
+ void (*running)(struct task_struct *p);
+
+ /**
+ * stopping - A task is stopping execution
+ * @p: task stopping to run
+ * @runnable: is task @p still runnable?
+ *
+ * See ->runnable() for explanation on the task state notifiers. If
+ * !@runnable, ->quiescent() will be invoked after this operation
+ * returns.
+ */
+ void (*stopping)(struct task_struct *p, bool runnable);
+
+ /**
+ * quiescent - A task is becoming not runnable on its associated CPU
+ * @p: task becoming not runnable
+ * @deq_flags: %SCX_DEQ_*
+ *
+ * See ->runnable() for explanation on the task state notifiers.
+ *
+ * @p is becoming quiescent on the CPU because it's
+ *
+ * - sleeping (%SCX_DEQ_SLEEP)
+ * - being moved to another CPU
+ * - being temporarily taken off the queue for an attribute change
+ * (%SCX_DEQ_SAVE)
+ *
+ * This and ->dequeue() are related but not coupled. This operation
+ * notifies @p's state transition and may not be preceded by ->dequeue()
+ * e.g. when @p is being dispatched to a remote CPU.
+ */
+ void (*quiescent)(struct task_struct *p, u64 deq_flags);
+
+ /**
+ * yield - Yield CPU
+ * @from: yielding task
+ * @to: optional yield target task
+ *
+ * If @to is NULL, @from is yielding the CPU to other runnable tasks.
+ * The BPF scheduler should ensure that other available tasks are
+ * dispatched before the yielding task. Return value is ignored in this
+ * case.
+ *
+ * If @to is not-NULL, @from wants to yield the CPU to @to. If the bpf
+ * scheduler can implement the request, return %true; otherwise, %false.
+ */
+ bool (*yield)(struct task_struct *from, struct task_struct *to);
+
+ /**
+ * core_sched_before - Task ordering for core-sched
+ * @a: task A
+ * @b: task B
+ *
+ * Used by core-sched to determine the ordering between two tasks. See
+ * Documentation/admin-guide/hw-vuln/core-scheduling.rst for details on
+ * core-sched.
+ *
+ * Both @a and @b are runnable and may or may not currently be queued on
+ * the BPF scheduler. Should return %true if @a should run before @b.
+ * %false if there's no required ordering or @b should run before @a.
+ *
+ * If not specified, the default is ordering them according to when they
+ * became runnable.
+ */
+ bool (*core_sched_before)(struct task_struct *a, struct task_struct *b);
+
+ /**
+ * set_weight - Set task weight
+ * @p: task to set weight for
+ * @weight: new weight [1..10000]
+ *
+ * Update @p's weight to @weight.
+ */
+ void (*set_weight)(struct task_struct *p, u32 weight);
+
+ /**
+ * set_cpumask - Set CPU affinity
+ * @p: task to set CPU affinity for
+ * @cpumask: cpumask of cpus that @p can run on
+ *
+ * Update @p's CPU affinity to @cpumask.
+ */
+ void (*set_cpumask)(struct task_struct *p,
+ const struct cpumask *cpumask);
+
+ /**
+ * update_idle - Update the idle state of a CPU
+ * @cpu: CPU to udpate the idle state for
+ * @idle: whether entering or exiting the idle state
+ *
+ * This operation is called when @rq's CPU goes or leaves the idle
+ * state. By default, implementing this operation disables the built-in
+ * idle CPU tracking and the following helpers become unavailable:
+ *
+ * - scx_bpf_select_cpu_dfl()
+ * - scx_bpf_test_and_clear_cpu_idle()
+ * - scx_bpf_pick_idle_cpu()
+ *
+ * The user also must implement ops.select_cpu() as the default
+ * implementation relies on scx_bpf_select_cpu_dfl().
+ *
+ * Specify the %SCX_OPS_KEEP_BUILTIN_IDLE flag to keep the built-in idle
+ * tracking.
+ */
+ void (*update_idle)(s32 cpu, bool idle);
+
+ /**
+ * cpu_acquire - A CPU is becoming available to the BPF scheduler
+ * @cpu: The CPU being acquired by the BPF scheduler.
+ * @args: Acquire arguments, see the struct definition.
+ *
+ * A CPU that was previously released from the BPF scheduler is now once
+ * again under its control.
+ */
+ void (*cpu_acquire)(s32 cpu, struct scx_cpu_acquire_args *args);
+
+ /**
+ * cpu_release - A CPU is taken away from the BPF scheduler
+ * @cpu: The CPU being released by the BPF scheduler.
+ * @args: Release arguments, see the struct definition.
+ *
+ * The specified CPU is no longer under the control of the BPF
+ * scheduler. This could be because it was preempted by a higher
+ * priority sched_class, though there may be other reasons as well. The
+ * caller should consult @args->reason to determine the cause.
+ */
+ void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);
+
+ /**
+ * init_task - Initialize a task to run in a BPF scheduler
+ * @p: task to initialize for BPF scheduling
+ * @args: init arguments, see the struct definition
+ *
+ * Either we're loading a BPF scheduler or a new task is being forked.
+ * Initialize @p for BPF scheduling. This operation may block and can
+ * be used for allocations, and is called exactly once for a task.
+ *
+ * Return 0 for success, -errno for failure. An error return while
+ * loading will abort loading of the BPF scheduler. During a fork, it
+ * will abort that specific fork.
+ */
+ s32 (*init_task)(struct task_struct *p, struct scx_init_task_args *args);
+
+ /**
+ * exit_task - Exit a previously-running task from the system
+ * @p: task to exit
+ *
+ * @p is exiting or the BPF scheduler is being unloaded. Perform any
+ * necessary cleanup for @p.
+ */
+ void (*exit_task)(struct task_struct *p, struct scx_exit_task_args *args);
+
+ /**
+ * enable - Enable BPF scheduling for a task
+ * @p: task to enable BPF scheduling for
+ *
+ * Enable @p for BPF scheduling. enable() is called on @p any time it
+ * enters SCX, and is always paired with a matching disable().
+ */
+ void (*enable)(struct task_struct *p);
+
+ /**
+ * disable - Disable BPF scheduling for a task
+ * @p: task to disable BPF scheduling for
+ *
+ * @p is exiting, leaving SCX or the BPF scheduler is being unloaded.
+ * Disable BPF scheduling for @p. A disable() call is always matched
+ * with a prior enable() call.
+ */
+ void (*disable)(struct task_struct *p);
+
+ /**
+ * dump - Dump BPF scheduler state on error
+ * @ctx: debug dump context
+ *
+ * Use scx_bpf_dump() to generate BPF scheduler specific debug dump.
+ */
+ void (*dump)(struct scx_dump_ctx *ctx);
+
+ /**
+ * dump_cpu - Dump BPF scheduler state for a CPU on error
+ * @ctx: debug dump context
+ * @cpu: CPU to generate debug dump for
+ * @idle: @cpu is currently idle without any runnable tasks
+ *
+ * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for
+ * @cpu. If @idle is %true and this operation doesn't produce any
+ * output, @cpu is skipped for dump.
+ */
+ void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle);
+
+ /**
+ * dump_task - Dump BPF scheduler state for a runnable task on error
+ * @ctx: debug dump context
+ * @p: runnable task to generate debug dump for
+ *
+ * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for
+ * @p.
+ */
+ void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p);
+
+#ifdef CONFIG_EXT_GROUP_SCHED
+ /**
+ * cgroup_init - Initialize a cgroup
+ * @cgrp: cgroup being initialized
+ * @args: init arguments, see the struct definition
+ *
+ * Either the BPF scheduler is being loaded or @cgrp created, initialize
+ * @cgrp for sched_ext. This operation may block.
+ *
+ * Return 0 for success, -errno for failure. An error return while
+ * loading will abort loading of the BPF scheduler. During cgroup
+ * creation, it will abort the specific cgroup creation.
+ */
+ s32 (*cgroup_init)(struct cgroup *cgrp,
+ struct scx_cgroup_init_args *args);
+
+ /**
+ * cgroup_exit - Exit a cgroup
+ * @cgrp: cgroup being exited
+ *
+ * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit
+ * @cgrp for sched_ext. This operation my block.
+ */
+ void (*cgroup_exit)(struct cgroup *cgrp);
+
+ /**
+ * cgroup_prep_move - Prepare a task to be moved to a different cgroup
+ * @p: task being moved
+ * @from: cgroup @p is being moved from
+ * @to: cgroup @p is being moved to
+ *
+ * Prepare @p for move from cgroup @from to @to. This operation may
+ * block and can be used for allocations.
+ *
+ * Return 0 for success, -errno for failure. An error return aborts the
+ * migration.
+ */
+ s32 (*cgroup_prep_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_move - Commit cgroup move
+ * @p: task being moved
+ * @from: cgroup @p is being moved from
+ * @to: cgroup @p is being moved to
+ *
+ * Commit the move. @p is dequeued during this operation.
+ */
+ void (*cgroup_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_cancel_move - Cancel cgroup move
+ * @p: task whose cgroup move is being canceled
+ * @from: cgroup @p was being moved from
+ * @to: cgroup @p was being moved to
+ *
+ * @p was cgroup_prep_move()'d but failed before reaching cgroup_move().
+ * Undo the preparation.
+ */
+ void (*cgroup_cancel_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_set_weight - A cgroup's weight is being changed
+ * @cgrp: cgroup whose weight is being updated
+ * @weight: new weight [1..10000]
+ *
+ * Update @tg's weight to @weight.
+ */
+ void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight);
+#endif /* CONFIG_CGROUPS */
+
+ /*
+ * All online ops must come before ops.cpu_online().
+ */
+
+ /**
+ * cpu_online - A CPU became online
+ * @cpu: CPU which just came up
+ *
+ * @cpu just came online. @cpu will not call ops.enqueue() or
+ * ops.dispatch(), nor run tasks associated with other CPUs beforehand.
+ */
+ void (*cpu_online)(s32 cpu);
+
+ /**
+ * cpu_offline - A CPU is going offline
+ * @cpu: CPU which is going offline
+ *
+ * @cpu is going offline. @cpu will not call ops.enqueue() or
+ * ops.dispatch(), nor run tasks associated with other CPUs afterwards.
+ */
+ void (*cpu_offline)(s32 cpu);
+
+ /*
+ * All CPU hotplug ops must come before ops.init().
+ */
+
+ /**
+ * init - Initialize the BPF scheduler
+ */
+ s32 (*init)(void);
+
+ /**
+ * exit - Clean up after the BPF scheduler
+ * @info: Exit info
+ */
+ void (*exit)(struct scx_exit_info *info);
+
+ /**
+ * dispatch_max_batch - Max nr of tasks that dispatch() can dispatch
+ */
+ u32 dispatch_max_batch;
+
+ /**
+ * flags - %SCX_OPS_* flags
+ */
+ u64 flags;
+
+ /**
+ * timeout_ms - The maximum amount of time, in milliseconds, that a
+ * runnable task should be able to wait before being scheduled. The
+ * maximum timeout may not exceed the default timeout of 30 seconds.
+ *
+ * Defaults to the maximum allowed timeout value of 30 seconds.
+ */
+ u32 timeout_ms;
+
+ /**
+ * exit_dump_len - scx_exit_info.dump buffer length. If 0, the default
+ * value of 32768 is used.
+ */
+ u32 exit_dump_len;
+
+ /**
+ * hotplug_seq - A sequence number that may be set by the scheduler to
+ * detect when a hotplug event has occurred during the loading process.
+ * If 0, no detection occurs. Otherwise, the scheduler will fail to
+ * load if the sequence number does not match @scx_hotplug_seq on the
+ * enable path.
+ */
+ u64 hotplug_seq;
+
+ /**
+ * name - BPF scheduler's name
+ *
+ * Must be a non-zero valid BPF object name including only isalnum(),
+ * '_' and '.' chars. Shows up in kernel.sched_ext_ops sysctl while the
+ * BPF scheduler is enabled.
+ */
+ char name[SCX_OPS_NAME_LEN];
+};
+
+enum scx_opi {
+ SCX_OPI_BEGIN = 0,
+ SCX_OPI_NORMAL_BEGIN = 0,
+ SCX_OPI_NORMAL_END = SCX_OP_IDX(cpu_online),
+ SCX_OPI_CPU_HOTPLUG_BEGIN = SCX_OP_IDX(cpu_online),
+ SCX_OPI_CPU_HOTPLUG_END = SCX_OP_IDX(init),
+ SCX_OPI_END = SCX_OP_IDX(init),
+};
+
+enum scx_wake_flags {
+ /* expose select WF_* flags as enums */
+ SCX_WAKE_FORK = WF_FORK,
+ SCX_WAKE_TTWU = WF_TTWU,
+ SCX_WAKE_SYNC = WF_SYNC,
+};
+
+enum scx_enq_flags {
+ /* expose select ENQUEUE_* flags as enums */
+ SCX_ENQ_WAKEUP = ENQUEUE_WAKEUP,
+ SCX_ENQ_HEAD = ENQUEUE_HEAD,
+
+ /* high 32bits are SCX specific */
+
+ /*
+ * Set the following to trigger preemption when calling
+ * scx_bpf_dispatch() with a local dsq as the target. The slice of the
+ * current task is cleared to zero and the CPU is kicked into the
+ * scheduling path. Implies %SCX_ENQ_HEAD.
+ */
+ SCX_ENQ_PREEMPT = 1LLU << 32,
+
+ /*
+ * The task being enqueued was previously enqueued on the current CPU's
+ * %SCX_DSQ_LOCAL, but was removed from it in a call to the
+ * bpf_scx_reenqueue_local() kfunc. If bpf_scx_reenqueue_local() was
+ * invoked in a ->cpu_release() callback, and the task is again
+ * dispatched back to %SCX_LOCAL_DSQ by this current ->enqueue(), the
+ * task will not be scheduled on the CPU until at least the next invocation
+ * of the ->cpu_acquire() callback.
+ */
+ SCX_ENQ_REENQ = 1LLU << 40,
+
+ /*
+ * The task being enqueued is the only task available for the cpu. By
+ * default, ext core keeps executing such tasks but when
+ * %SCX_OPS_ENQ_LAST is specified, they're ops.enqueue()'d with the
+ * %SCX_ENQ_LAST flag set.
+ *
+ * If the BPF scheduler wants to continue executing the task,
+ * ops.enqueue() should dispatch the task to %SCX_DSQ_LOCAL immediately.
+ * If the task gets queued on a different dsq or the BPF side, the BPF
+ * scheduler is responsible for triggering a follow-up scheduling event.
+ * Otherwise, Execution may stall.
+ */
+ SCX_ENQ_LAST = 1LLU << 41,
+
+ /* high 8 bits are internal */
+ __SCX_ENQ_INTERNAL_MASK = 0xffLLU << 56,
+
+ SCX_ENQ_CLEAR_OPSS = 1LLU << 56,
+ SCX_ENQ_DSQ_PRIQ = 1LLU << 57,
+};
+
+enum scx_deq_flags {
+ /* expose select DEQUEUE_* flags as enums */
+ SCX_DEQ_SLEEP = DEQUEUE_SLEEP,
+
+ /* high 32bits are SCX specific */
+
+ /*
+ * The generic core-sched layer decided to execute the task even though
+ * it hasn't been dispatched yet. Dequeue from the BPF side.
+ */
+ SCX_DEQ_CORE_SCHED_EXEC = 1LLU << 32,
+};
+
+enum scx_pick_idle_cpu_flags {
+ SCX_PICK_IDLE_CORE = 1LLU << 0, /* pick a CPU whose SMT siblings are also idle */
+};
+
+enum scx_kick_flags {
+ /*
+ * Kick the target CPU if idle. Guarantees that the target CPU goes
+ * through at least one full scheduling cycle before going idle. If the
+ * target CPU can be determined to be currently not idle and going to go
+ * through a scheduling cycle before going idle, noop.
+ */
+ SCX_KICK_IDLE = 1LLU << 0,
+
+ /*
+ * Preempt the current task and execute the dispatch path. If the
+ * current task of the target CPU is an SCX task, its ->scx.slice is
+ * cleared to zero before the scheduling path is invoked so that the
+ * task expires and the dispatch path is invoked.
+ */
+ SCX_KICK_PREEMPT = 1LLU << 1,
+
+ /*
+ * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will
+ * return after the target CPU finishes picking the next task.
+ */
+ SCX_KICK_WAIT = 1LLU << 2,
+};
+
+enum scx_tg_flags {
+ SCX_TG_ONLINE = 1U << 0,
+ SCX_TG_INITED = 1U << 1,
+};
+
+enum scx_ops_enable_state {
+ SCX_OPS_ENABLING,
+ SCX_OPS_ENABLED,
+ SCX_OPS_DISABLING,
+ SCX_OPS_DISABLED,
+};
+
+static const char *scx_ops_enable_state_str[] = {
+ [SCX_OPS_ENABLING] = "enabling",
+ [SCX_OPS_ENABLED] = "enabled",
+ [SCX_OPS_DISABLING] = "disabling",
+ [SCX_OPS_DISABLED] = "disabled",
+};
+
+/*
+ * sched_ext_entity->ops_state
+ *
+ * Used to track the task ownership between the SCX core and the BPF scheduler.
+ * State transitions look as follows:
+ *
+ * NONE -> QUEUEING -> QUEUED -> DISPATCHING
+ * ^ | |
+ * | v v
+ * \-------------------------------/
+ *
+ * QUEUEING and DISPATCHING states can be waited upon. See wait_ops_state() call
+ * sites for explanations on the conditions being waited upon and why they are
+ * safe. Transitions out of them into NONE or QUEUED must store_release and the
+ * waiters should load_acquire.
+ *
+ * Tracking scx_ops_state enables sched_ext core to reliably determine whether
+ * any given task can be dispatched by the BPF scheduler at all times and thus
+ * relaxes the requirements on the BPF scheduler. This allows the BPF scheduler
+ * to try to dispatch any task anytime regardless of its state as the SCX core
+ * can safely reject invalid dispatches.
+ */
+enum scx_ops_state {
+ SCX_OPSS_NONE, /* owned by the SCX core */
+ SCX_OPSS_QUEUEING, /* in transit to the BPF scheduler */
+ SCX_OPSS_QUEUED, /* owned by the BPF scheduler */
+ SCX_OPSS_DISPATCHING, /* in transit back to the SCX core */
+
+ /*
+ * QSEQ brands each QUEUED instance so that, when dispatch races
+ * dequeue/requeue, the dispatcher can tell whether it still has a claim
+ * on the task being dispatched.
+ *
+ * As some 32bit archs can't do 64bit store_release/load_acquire,
+ * p->scx.ops_state is atomic_long_t which leaves 30 bits for QSEQ on
+ * 32bit machines. The dispatch race window QSEQ protects is very narrow
+ * and runs with IRQ disabled. 30 bits should be sufficient.
+ */
+ SCX_OPSS_QSEQ_SHIFT = 2,
+};
+
+/* Use macros to ensure that the type is unsigned long for the masks */
+#define SCX_OPSS_STATE_MASK ((1LU << SCX_OPSS_QSEQ_SHIFT) - 1)
+#define SCX_OPSS_QSEQ_MASK (~SCX_OPSS_STATE_MASK)
+
+/*
+ * During exit, a task may schedule after losing its PIDs. When disabling the
+ * BPF scheduler, we need to be able to iterate tasks in every state to
+ * guarantee system safety. Maintain a dedicated task list which contains every
+ * task between its fork and eventual free.
+ */
+static DEFINE_SPINLOCK(scx_tasks_lock);
+static LIST_HEAD(scx_tasks);
+
+/* ops enable/disable */
+static struct kthread_worker *scx_ops_helper;
+static DEFINE_MUTEX(scx_ops_enable_mutex);
+DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled);
+DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem);
+static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED);
+static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0);
+static bool scx_ops_init_task_enabled;
+static bool scx_switching_all;
+DEFINE_STATIC_KEY_FALSE(__scx_switched_all);
+
+static struct sched_ext_ops scx_ops;
+static bool scx_warned_zero_slice;
+
+static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last);
+static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting);
+static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt);
+static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled);
+
+static struct static_key_false scx_has_op[SCX_OPI_END] =
+ { [0 ... SCX_OPI_END-1] = STATIC_KEY_FALSE_INIT };
+
+static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE);
+static struct scx_exit_info *scx_exit_info;
+
+static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0);
+static atomic_long_t scx_hotplug_seq = ATOMIC_LONG_INIT(0);
+
+/*
+ * A monotically increasing sequence number that is incremented every time a
+ * scheduler is enabled. This can be used by to check if any custom sched_ext
+ * scheduler has ever been used in the system.
+ */
+static atomic_long_t scx_enable_seq = ATOMIC_LONG_INIT(0);
+
+/*
+ * The maximum amount of time in jiffies that a task may be runnable without
+ * being scheduled on a CPU. If this timeout is exceeded, it will trigger
+ * scx_ops_error().
+ */
+static unsigned long scx_watchdog_timeout;
+
+/*
+ * The last time the delayed work was run. This delayed work relies on
+ * ksoftirqd being able to run to service timer interrupts, so it's possible
+ * that this work itself could get wedged. To account for this, we check that
+ * it's not stalled in the timer tick, and trigger an error if it is.
+ */
+static unsigned long scx_watchdog_timestamp = INITIAL_JIFFIES;
+
+static struct delayed_work scx_watchdog_work;
+
+/* idle tracking */
+#ifdef CONFIG_SMP
+#ifdef CONFIG_CPUMASK_OFFSTACK
+#define CL_ALIGNED_IF_ONSTACK
+#else
+#define CL_ALIGNED_IF_ONSTACK __cacheline_aligned_in_smp
+#endif
+
+static struct {
+ cpumask_var_t cpu;
+ cpumask_var_t smt;
+} idle_masks CL_ALIGNED_IF_ONSTACK;
+
+#endif /* CONFIG_SMP */
+
+/* for %SCX_KICK_WAIT */
+static unsigned long __percpu *scx_kick_cpus_pnt_seqs;
+
+/*
+ * Direct dispatch marker.
+ *
+ * Non-NULL values are used for direct dispatch from enqueue path. A valid
+ * pointer points to the task currently being enqueued. An ERR_PTR value is used
+ * to indicate that direct dispatch has already happened.
+ */
+static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task);
+
+/*
+ * Dispatch queues.
+ *
+ * The global DSQ (%SCX_DSQ_GLOBAL) is split per-node for scalability. This is
+ * to avoid live-locking in bypass mode where all tasks are dispatched to
+ * %SCX_DSQ_GLOBAL and all CPUs consume from it. If per-node split isn't
+ * sufficient, it can be further split.
+ */
+static struct scx_dispatch_q **global_dsqs;
+
+static const struct rhashtable_params dsq_hash_params = {
+ .key_len = 8,
+ .key_offset = offsetof(struct scx_dispatch_q, id),
+ .head_offset = offsetof(struct scx_dispatch_q, hash_node),
+};
+
+static struct rhashtable dsq_hash;
+static LLIST_HEAD(dsqs_to_free);
+
+/* dispatch buf */
+struct scx_dsp_buf_ent {
+ struct task_struct *task;
+ unsigned long qseq;
+ u64 dsq_id;
+ u64 enq_flags;
+};
+
+static u32 scx_dsp_max_batch;
+
+struct scx_dsp_ctx {
+ struct rq *rq;
+ u32 cursor;
+ u32 nr_tasks;
+ struct scx_dsp_buf_ent buf[];
+};
+
+static struct scx_dsp_ctx __percpu *scx_dsp_ctx;
+
+/* string formatting from BPF */
+struct scx_bstr_buf {
+ u64 data[MAX_BPRINTF_VARARGS];
+ char line[SCX_EXIT_MSG_LEN];
+};
+
+static DEFINE_RAW_SPINLOCK(scx_exit_bstr_buf_lock);
+static struct scx_bstr_buf scx_exit_bstr_buf;
+
+/* ops debug dump */
+struct scx_dump_data {
+ s32 cpu;
+ bool first;
+ s32 cursor;
+ struct seq_buf *s;
+ const char *prefix;
+ struct scx_bstr_buf buf;
+};
+
+static struct scx_dump_data scx_dump_data = {
+ .cpu = -1,
+};
+
+/* /sys/kernel/sched_ext interface */
+static struct kset *scx_kset;
+static struct kobject *scx_root_kobj;
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched_ext.h>
+
+static void process_ddsp_deferred_locals(struct rq *rq);
+static void scx_bpf_kick_cpu(s32 cpu, u64 flags);
+static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
+ s64 exit_code,
+ const char *fmt, ...);
+
+#define scx_ops_error_kind(err, fmt, args...) \
+ scx_ops_exit_kind((err), 0, fmt, ##args)
+
+#define scx_ops_exit(code, fmt, args...) \
+ scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args)
+
+#define scx_ops_error(fmt, args...) \
+ scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args)
+
+#define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)])
+
+static long jiffies_delta_msecs(unsigned long at, unsigned long now)
+{
+ if (time_after(at, now))
+ return jiffies_to_msecs(at - now);
+ else
+ return -(long)jiffies_to_msecs(now - at);
+}
+
+/* if the highest set bit is N, return a mask with bits [N+1, 31] set */
+static u32 higher_bits(u32 flags)
+{
+ return ~((1 << fls(flags)) - 1);
+}
+
+/* return the mask with only the highest bit set */
+static u32 highest_bit(u32 flags)
+{
+ int bit = fls(flags);
+ return ((u64)1 << bit) >> 1;
+}
+
+static bool u32_before(u32 a, u32 b)
+{
+ return (s32)(a - b) < 0;
+}
+
+static struct scx_dispatch_q *find_global_dsq(struct task_struct *p)
+{
+ return global_dsqs[cpu_to_node(task_cpu(p))];
+}
+
+static struct scx_dispatch_q *find_user_dsq(u64 dsq_id)
+{
+ return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params);
+}
+
+/*
+ * scx_kf_mask enforcement. Some kfuncs can only be called from specific SCX
+ * ops. When invoking SCX ops, SCX_CALL_OP[_RET]() should be used to indicate
+ * the allowed kfuncs and those kfuncs should use scx_kf_allowed() to check
+ * whether it's running from an allowed context.
+ *
+ * @mask is constant, always inline to cull the mask calculations.
+ */
+static __always_inline void scx_kf_allow(u32 mask)
+{
+ /* nesting is allowed only in increasing scx_kf_mask order */
+ WARN_ONCE((mask | higher_bits(mask)) & current->scx.kf_mask,
+ "invalid nesting current->scx.kf_mask=0x%x mask=0x%x\n",
+ current->scx.kf_mask, mask);
+ current->scx.kf_mask |= mask;
+ barrier();
+}
+
+static void scx_kf_disallow(u32 mask)
+{
+ barrier();
+ current->scx.kf_mask &= ~mask;
+}
+
+#define SCX_CALL_OP(mask, op, args...) \
+do { \
+ if (mask) { \
+ scx_kf_allow(mask); \
+ scx_ops.op(args); \
+ scx_kf_disallow(mask); \
+ } else { \
+ scx_ops.op(args); \
+ } \
+} while (0)
+
+#define SCX_CALL_OP_RET(mask, op, args...) \
+({ \
+ __typeof__(scx_ops.op(args)) __ret; \
+ if (mask) { \
+ scx_kf_allow(mask); \
+ __ret = scx_ops.op(args); \
+ scx_kf_disallow(mask); \
+ } else { \
+ __ret = scx_ops.op(args); \
+ } \
+ __ret; \
+})
+
+/*
+ * Some kfuncs are allowed only on the tasks that are subjects of the
+ * in-progress scx_ops operation for, e.g., locking guarantees. To enforce such
+ * restrictions, the following SCX_CALL_OP_*() variants should be used when
+ * invoking scx_ops operations that take task arguments. These can only be used
+ * for non-nesting operations due to the way the tasks are tracked.
+ *
+ * kfuncs which can only operate on such tasks can in turn use
+ * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on
+ * the specific task.
+ */
+#define SCX_CALL_OP_TASK(mask, op, task, args...) \
+do { \
+ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
+ current->scx.kf_tasks[0] = task; \
+ SCX_CALL_OP(mask, op, task, ##args); \
+ current->scx.kf_tasks[0] = NULL; \
+} while (0)
+
+#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \
+({ \
+ __typeof__(scx_ops.op(task, ##args)) __ret; \
+ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
+ current->scx.kf_tasks[0] = task; \
+ __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \
+ current->scx.kf_tasks[0] = NULL; \
+ __ret; \
+})
+
+#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \
+({ \
+ __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \
+ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \
+ current->scx.kf_tasks[0] = task0; \
+ current->scx.kf_tasks[1] = task1; \
+ __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \
+ current->scx.kf_tasks[0] = NULL; \
+ current->scx.kf_tasks[1] = NULL; \
+ __ret; \
+})
+
+/* @mask is constant, always inline to cull unnecessary branches */
+static __always_inline bool scx_kf_allowed(u32 mask)
+{
+ if (unlikely(!(current->scx.kf_mask & mask))) {
+ scx_ops_error("kfunc with mask 0x%x called from an operation only allowing 0x%x",
+ mask, current->scx.kf_mask);
+ return false;
+ }
+
+ /*
+ * Enforce nesting boundaries. e.g. A kfunc which can be called from
+ * DISPATCH must not be called if we're running DEQUEUE which is nested
+ * inside ops.dispatch(). We don't need to check boundaries for any
+ * blocking kfuncs as the verifier ensures they're only called from
+ * sleepable progs.
+ */
+ if (unlikely(highest_bit(mask) == SCX_KF_CPU_RELEASE &&
+ (current->scx.kf_mask & higher_bits(SCX_KF_CPU_RELEASE)))) {
+ scx_ops_error("cpu_release kfunc called from a nested operation");
+ return false;
+ }
+
+ if (unlikely(highest_bit(mask) == SCX_KF_DISPATCH &&
+ (current->scx.kf_mask & higher_bits(SCX_KF_DISPATCH)))) {
+ scx_ops_error("dispatch kfunc called from a nested operation");
+ return false;
+ }
+
+ return true;
+}
+
+/* see SCX_CALL_OP_TASK() */
+static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask,
+ struct task_struct *p)
+{
+ if (!scx_kf_allowed(mask))
+ return false;
+
+ if (unlikely((p != current->scx.kf_tasks[0] &&
+ p != current->scx.kf_tasks[1]))) {
+ scx_ops_error("called on a task not being operated on");
+ return false;
+ }
+
+ return true;
+}
+
+static bool scx_kf_allowed_if_unlocked(void)
+{
+ return !current->scx.kf_mask;
+}
+
+/**
+ * nldsq_next_task - Iterate to the next task in a non-local DSQ
+ * @dsq: user dsq being interated
+ * @cur: current position, %NULL to start iteration
+ * @rev: walk backwards
+ *
+ * Returns %NULL when iteration is finished.
+ */
+static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq,
+ struct task_struct *cur, bool rev)
+{
+ struct list_head *list_node;
+ struct scx_dsq_list_node *dsq_lnode;
+
+ lockdep_assert_held(&dsq->lock);
+
+ if (cur)
+ list_node = &cur->scx.dsq_list.node;
+ else
+ list_node = &dsq->list;
+
+ /* find the next task, need to skip BPF iteration cursors */
+ do {
+ if (rev)
+ list_node = list_node->prev;
+ else
+ list_node = list_node->next;
+
+ if (list_node == &dsq->list)
+ return NULL;
+
+ dsq_lnode = container_of(list_node, struct scx_dsq_list_node,
+ node);
+ } while (dsq_lnode->flags & SCX_DSQ_LNODE_ITER_CURSOR);
+
+ return container_of(dsq_lnode, struct task_struct, scx.dsq_list);
+}
+
+#define nldsq_for_each_task(p, dsq) \
+ for ((p) = nldsq_next_task((dsq), NULL, false); (p); \
+ (p) = nldsq_next_task((dsq), (p), false))
+
+
+/*
+ * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse]
+ * dispatch order. BPF-visible iterator is opaque and larger to allow future
+ * changes without breaking backward compatibility. Can be used with
+ * bpf_for_each(). See bpf_iter_scx_dsq_*().
+ */
+enum scx_dsq_iter_flags {
+ /* iterate in the reverse dispatch order */
+ SCX_DSQ_ITER_REV = 1U << 16,
+
+ __SCX_DSQ_ITER_HAS_SLICE = 1U << 30,
+ __SCX_DSQ_ITER_HAS_VTIME = 1U << 31,
+
+ __SCX_DSQ_ITER_USER_FLAGS = SCX_DSQ_ITER_REV,
+ __SCX_DSQ_ITER_ALL_FLAGS = __SCX_DSQ_ITER_USER_FLAGS |
+ __SCX_DSQ_ITER_HAS_SLICE |
+ __SCX_DSQ_ITER_HAS_VTIME,
+};
+
+struct bpf_iter_scx_dsq_kern {
+ struct scx_dsq_list_node cursor;
+ struct scx_dispatch_q *dsq;
+ u64 slice;
+ u64 vtime;
+} __attribute__((aligned(8)));
+
+struct bpf_iter_scx_dsq {
+ u64 __opaque[6];
+} __attribute__((aligned(8)));
+
+
+/*
+ * SCX task iterator.
+ */
+struct scx_task_iter {
+ struct sched_ext_entity cursor;
+ struct task_struct *locked;
+ struct rq *rq;
+ struct rq_flags rf;
+ u32 cnt;
+};
+
+/**
+ * scx_task_iter_start - Lock scx_tasks_lock and start a task iteration
+ * @iter: iterator to init
+ *
+ * Initialize @iter and return with scx_tasks_lock held. Once initialized, @iter
+ * must eventually be stopped with scx_task_iter_stop().
+ *
+ * scx_tasks_lock and the rq lock may be released using scx_task_iter_unlock()
+ * between this and the first next() call or between any two next() calls. If
+ * the locks are released between two next() calls, the caller is responsible
+ * for ensuring that the task being iterated remains accessible either through
+ * RCU read lock or obtaining a reference count.
+ *
+ * All tasks which existed when the iteration started are guaranteed to be
+ * visited as long as they still exist.
+ */
+static void scx_task_iter_start(struct scx_task_iter *iter)
+{
+ BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
+ ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
+
+ spin_lock_irq(&scx_tasks_lock);
+
+ iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
+ list_add(&iter->cursor.tasks_node, &scx_tasks);
+ iter->locked = NULL;
+ iter->cnt = 0;
+}
+
+static void __scx_task_iter_rq_unlock(struct scx_task_iter *iter)
+{
+ if (iter->locked) {
+ task_rq_unlock(iter->rq, iter->locked, &iter->rf);
+ iter->locked = NULL;
+ }
+}
+
+/**
+ * scx_task_iter_unlock - Unlock rq and scx_tasks_lock held by a task iterator
+ * @iter: iterator to unlock
+ *
+ * If @iter is in the middle of a locked iteration, it may be locking the rq of
+ * the task currently being visited in addition to scx_tasks_lock. Unlock both.
+ * This function can be safely called anytime during an iteration.
+ */
+static void scx_task_iter_unlock(struct scx_task_iter *iter)
+{
+ __scx_task_iter_rq_unlock(iter);
+ spin_unlock_irq(&scx_tasks_lock);
+}
+
+/**
+ * scx_task_iter_relock - Lock scx_tasks_lock released by scx_task_iter_unlock()
+ * @iter: iterator to re-lock
+ *
+ * Re-lock scx_tasks_lock unlocked by scx_task_iter_unlock(). Note that it
+ * doesn't re-lock the rq lock. Must be called before other iterator operations.
+ */
+static void scx_task_iter_relock(struct scx_task_iter *iter)
+{
+ spin_lock_irq(&scx_tasks_lock);
+}
+
+/**
+ * scx_task_iter_stop - Stop a task iteration and unlock scx_tasks_lock
+ * @iter: iterator to exit
+ *
+ * Exit a previously initialized @iter. Must be called with scx_tasks_lock held
+ * which is released on return. If the iterator holds a task's rq lock, that rq
+ * lock is also released. See scx_task_iter_start() for details.
+ */
+static void scx_task_iter_stop(struct scx_task_iter *iter)
+{
+ list_del_init(&iter->cursor.tasks_node);
+ scx_task_iter_unlock(iter);
+}
+
+/**
+ * scx_task_iter_next - Next task
+ * @iter: iterator to walk
+ *
+ * Visit the next task. See scx_task_iter_start() for details. Locks are dropped
+ * and re-acquired every %SCX_OPS_TASK_ITER_BATCH iterations to avoid causing
+ * stalls by holding scx_tasks_lock for too long.
+ */
+static struct task_struct *scx_task_iter_next(struct scx_task_iter *iter)
+{
+ struct list_head *cursor = &iter->cursor.tasks_node;
+ struct sched_ext_entity *pos;
+
+ if (!(++iter->cnt % SCX_OPS_TASK_ITER_BATCH)) {
+ scx_task_iter_unlock(iter);
+ cpu_relax();
+ cond_resched();
+ scx_task_iter_relock(iter);
+ }
+
+ list_for_each_entry(pos, cursor, tasks_node) {
+ if (&pos->tasks_node == &scx_tasks)
+ return NULL;
+ if (!(pos->flags & SCX_TASK_CURSOR)) {
+ list_move(cursor, &pos->tasks_node);
+ return container_of(pos, struct task_struct, scx);
+ }
+ }
+
+ /* can't happen, should always terminate at scx_tasks above */
+ BUG();
+}
+
+/**
+ * scx_task_iter_next_locked - Next non-idle task with its rq locked
+ * @iter: iterator to walk
+ * @include_dead: Whether we should include dead tasks in the iteration
+ *
+ * Visit the non-idle task with its rq lock held. Allows callers to specify
+ * whether they would like to filter out dead tasks. See scx_task_iter_start()
+ * for details.
+ */
+static struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter)
+{
+ struct task_struct *p;
+
+ __scx_task_iter_rq_unlock(iter);
+
+ while ((p = scx_task_iter_next(iter))) {
+ /*
+ * scx_task_iter is used to prepare and move tasks into SCX
+ * while loading the BPF scheduler and vice-versa while
+ * unloading. The init_tasks ("swappers") should be excluded
+ * from the iteration because:
+ *
+ * - It's unsafe to use __setschduler_prio() on an init_task to
+ * determine the sched_class to use as it won't preserve its
+ * idle_sched_class.
+ *
+ * - ops.init/exit_task() can easily be confused if called with
+ * init_tasks as they, e.g., share PID 0.
+ *
+ * As init_tasks are never scheduled through SCX, they can be
+ * skipped safely. Note that is_idle_task() which tests %PF_IDLE
+ * doesn't work here:
+ *
+ * - %PF_IDLE may not be set for an init_task whose CPU hasn't
+ * yet been onlined.
+ *
+ * - %PF_IDLE can be set on tasks that are not init_tasks. See
+ * play_idle_precise() used by CONFIG_IDLE_INJECT.
+ *
+ * Test for idle_sched_class as only init_tasks are on it.
+ */
+ if (p->sched_class != &idle_sched_class)
+ break;
+ }
+ if (!p)
+ return NULL;
+
+ iter->rq = task_rq_lock(p, &iter->rf);
+ iter->locked = p;
+
+ return p;
+}
+
+static enum scx_ops_enable_state scx_ops_enable_state(void)
+{
+ return atomic_read(&scx_ops_enable_state_var);
+}
+
+static enum scx_ops_enable_state
+scx_ops_set_enable_state(enum scx_ops_enable_state to)
+{
+ return atomic_xchg(&scx_ops_enable_state_var, to);
+}
+
+static bool scx_ops_tryset_enable_state(enum scx_ops_enable_state to,
+ enum scx_ops_enable_state from)
+{
+ int from_v = from;
+
+ return atomic_try_cmpxchg(&scx_ops_enable_state_var, &from_v, to);
+}
+
+static bool scx_rq_bypassing(struct rq *rq)
+{
+ return unlikely(rq->scx.flags & SCX_RQ_BYPASSING);
+}
+
+/**
+ * wait_ops_state - Busy-wait the specified ops state to end
+ * @p: target task
+ * @opss: state to wait the end of
+ *
+ * Busy-wait for @p to transition out of @opss. This can only be used when the
+ * state part of @opss is %SCX_QUEUEING or %SCX_DISPATCHING. This function also
+ * has load_acquire semantics to ensure that the caller can see the updates made
+ * in the enqueueing and dispatching paths.
+ */
+static void wait_ops_state(struct task_struct *p, unsigned long opss)
+{
+ do {
+ cpu_relax();
+ } while (atomic_long_read_acquire(&p->scx.ops_state) == opss);
+}
+
+/**
+ * ops_cpu_valid - Verify a cpu number
+ * @cpu: cpu number which came from a BPF ops
+ * @where: extra information reported on error
+ *
+ * @cpu is a cpu number which came from the BPF scheduler and can be any value.
+ * Verify that it is in range and one of the possible cpus. If invalid, trigger
+ * an ops error.
+ */
+static bool ops_cpu_valid(s32 cpu, const char *where)
+{
+ if (likely(cpu >= 0 && cpu < nr_cpu_ids && cpu_possible(cpu))) {
+ return true;
+ } else {
+ scx_ops_error("invalid CPU %d%s%s", cpu,
+ where ? " " : "", where ?: "");
+ return false;
+ }
+}
+
+/**
+ * ops_sanitize_err - Sanitize a -errno value
+ * @ops_name: operation to blame on failure
+ * @err: -errno value to sanitize
+ *
+ * Verify @err is a valid -errno. If not, trigger scx_ops_error() and return
+ * -%EPROTO. This is necessary because returning a rogue -errno up the chain can
+ * cause misbehaviors. For an example, a large negative return from
+ * ops.init_task() triggers an oops when passed up the call chain because the
+ * value fails IS_ERR() test after being encoded with ERR_PTR() and then is
+ * handled as a pointer.
+ */
+static int ops_sanitize_err(const char *ops_name, s32 err)
+{
+ if (err < 0 && err >= -MAX_ERRNO)
+ return err;
+
+ scx_ops_error("ops.%s() returned an invalid errno %d", ops_name, err);
+ return -EPROTO;
+}
+
+static void run_deferred(struct rq *rq)
+{
+ process_ddsp_deferred_locals(rq);
+}
+
+#ifdef CONFIG_SMP
+static void deferred_bal_cb_workfn(struct rq *rq)
+{
+ run_deferred(rq);
+}
+#endif
+
+static void deferred_irq_workfn(struct irq_work *irq_work)
+{
+ struct rq *rq = container_of(irq_work, struct rq, scx.deferred_irq_work);
+
+ raw_spin_rq_lock(rq);
+ run_deferred(rq);
+ raw_spin_rq_unlock(rq);
+}
+
+/**
+ * schedule_deferred - Schedule execution of deferred actions on an rq
+ * @rq: target rq
+ *
+ * Schedule execution of deferred actions on @rq. Must be called with @rq
+ * locked. Deferred actions are executed with @rq locked but unpinned, and thus
+ * can unlock @rq to e.g. migrate tasks to other rqs.
+ */
+static void schedule_deferred(struct rq *rq)
+{
+ lockdep_assert_rq_held(rq);
+
+#ifdef CONFIG_SMP
+ /*
+ * If in the middle of waking up a task, task_woken_scx() will be called
+ * afterwards which will then run the deferred actions, no need to
+ * schedule anything.
+ */
+ if (rq->scx.flags & SCX_RQ_IN_WAKEUP)
+ return;
+
+ /*
+ * If in balance, the balance callbacks will be called before rq lock is
+ * released. Schedule one.
+ */
+ if (rq->scx.flags & SCX_RQ_IN_BALANCE) {
+ queue_balance_callback(rq, &rq->scx.deferred_bal_cb,
+ deferred_bal_cb_workfn);
+ return;
+ }
+#endif
+ /*
+ * No scheduler hooks available. Queue an irq work. They are executed on
+ * IRQ re-enable which may take a bit longer than the scheduler hooks.
+ * The above WAKEUP and BALANCE paths should cover most of the cases and
+ * the time to IRQ re-enable shouldn't be long.
+ */
+ irq_work_queue(&rq->scx.deferred_irq_work);
+}
+
+/**
+ * touch_core_sched - Update timestamp used for core-sched task ordering
+ * @rq: rq to read clock from, must be locked
+ * @p: task to update the timestamp for
+ *
+ * Update @p->scx.core_sched_at timestamp. This is used by scx_prio_less() to
+ * implement global or local-DSQ FIFO ordering for core-sched. Should be called
+ * when a task becomes runnable and its turn on the CPU ends (e.g. slice
+ * exhaustion).
+ */
+static void touch_core_sched(struct rq *rq, struct task_struct *p)
+{
+ lockdep_assert_rq_held(rq);
+
+#ifdef CONFIG_SCHED_CORE
+ /*
+ * It's okay to update the timestamp spuriously. Use
+ * sched_core_disabled() which is cheaper than enabled().
+ *
+ * As this is used to determine ordering between tasks of sibling CPUs,
+ * it may be better to use per-core dispatch sequence instead.
+ */
+ if (!sched_core_disabled())
+ p->scx.core_sched_at = sched_clock_cpu(cpu_of(rq));
+#endif
+}
+
+/**
+ * touch_core_sched_dispatch - Update core-sched timestamp on dispatch
+ * @rq: rq to read clock from, must be locked
+ * @p: task being dispatched
+ *
+ * If the BPF scheduler implements custom core-sched ordering via
+ * ops.core_sched_before(), @p->scx.core_sched_at is used to implement FIFO
+ * ordering within each local DSQ. This function is called from dispatch paths
+ * and updates @p->scx.core_sched_at if custom core-sched ordering is in effect.
+ */
+static void touch_core_sched_dispatch(struct rq *rq, struct task_struct *p)
+{
+ lockdep_assert_rq_held(rq);
+
+#ifdef CONFIG_SCHED_CORE
+ if (SCX_HAS_OP(core_sched_before))
+ touch_core_sched(rq, p);
+#endif
+}
+
+static void update_curr_scx(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ s64 delta_exec;
+
+ delta_exec = update_curr_common(rq);
+ if (unlikely(delta_exec <= 0))
+ return;
+
+ if (curr->scx.slice != SCX_SLICE_INF) {
+ curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec);
+ if (!curr->scx.slice)
+ touch_core_sched(rq, curr);
+ }
+}
+
+static bool scx_dsq_priq_less(struct rb_node *node_a,
+ const struct rb_node *node_b)
+{
+ const struct task_struct *a =
+ container_of(node_a, struct task_struct, scx.dsq_priq);
+ const struct task_struct *b =
+ container_of(node_b, struct task_struct, scx.dsq_priq);
+
+ return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime);
+}
+
+static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta)
+{
+ /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */
+ WRITE_ONCE(dsq->nr, dsq->nr + delta);
+}
+
+static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p,
+ u64 enq_flags)
+{
+ bool is_local = dsq->id == SCX_DSQ_LOCAL;
+
+ WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
+ WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) ||
+ !RB_EMPTY_NODE(&p->scx.dsq_priq));
+
+ if (!is_local) {
+ raw_spin_lock(&dsq->lock);
+ if (unlikely(dsq->id == SCX_DSQ_INVALID)) {
+ scx_ops_error("attempting to dispatch to a destroyed dsq");
+ /* fall back to the global dsq */
+ raw_spin_unlock(&dsq->lock);
+ dsq = find_global_dsq(p);
+ raw_spin_lock(&dsq->lock);
+ }
+ }
+
+ if (unlikely((dsq->id & SCX_DSQ_FLAG_BUILTIN) &&
+ (enq_flags & SCX_ENQ_DSQ_PRIQ))) {
+ /*
+ * SCX_DSQ_LOCAL and SCX_DSQ_GLOBAL DSQs always consume from
+ * their FIFO queues. To avoid confusion and accidentally
+ * starving vtime-dispatched tasks by FIFO-dispatched tasks, we
+ * disallow any internal DSQ from doing vtime ordering of
+ * tasks.
+ */
+ scx_ops_error("cannot use vtime ordering for built-in DSQs");
+ enq_flags &= ~SCX_ENQ_DSQ_PRIQ;
+ }
+
+ if (enq_flags & SCX_ENQ_DSQ_PRIQ) {
+ struct rb_node *rbp;
+
+ /*
+ * A PRIQ DSQ shouldn't be using FIFO enqueueing. As tasks are
+ * linked to both the rbtree and list on PRIQs, this can only be
+ * tested easily when adding the first task.
+ */
+ if (unlikely(RB_EMPTY_ROOT(&dsq->priq) &&
+ nldsq_next_task(dsq, NULL, false)))
+ scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks",
+ dsq->id);
+
+ p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ;
+ rb_add(&p->scx.dsq_priq, &dsq->priq, scx_dsq_priq_less);
+
+ /*
+ * Find the previous task and insert after it on the list so
+ * that @dsq->list is vtime ordered.
+ */
+ rbp = rb_prev(&p->scx.dsq_priq);
+ if (rbp) {
+ struct task_struct *prev =
+ container_of(rbp, struct task_struct,
+ scx.dsq_priq);
+ list_add(&p->scx.dsq_list.node, &prev->scx.dsq_list.node);
+ } else {
+ list_add(&p->scx.dsq_list.node, &dsq->list);
+ }
+ } else {
+ /* a FIFO DSQ shouldn't be using PRIQ enqueuing */
+ if (unlikely(!RB_EMPTY_ROOT(&dsq->priq)))
+ scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks",
+ dsq->id);
+
+ if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
+ list_add(&p->scx.dsq_list.node, &dsq->list);
+ else
+ list_add_tail(&p->scx.dsq_list.node, &dsq->list);
+ }
+
+ /* seq records the order tasks are queued, used by BPF DSQ iterator */
+ dsq->seq++;
+ p->scx.dsq_seq = dsq->seq;
+
+ dsq_mod_nr(dsq, 1);
+ p->scx.dsq = dsq;
+
+ /*
+ * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the
+ * direct dispatch path, but we clear them here because the direct
+ * dispatch verdict may be overridden on the enqueue path during e.g.
+ * bypass.
+ */
+ p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
+ p->scx.ddsp_enq_flags = 0;
+
+ /*
+ * We're transitioning out of QUEUEING or DISPATCHING. store_release to
+ * match waiters' load_acquire.
+ */
+ if (enq_flags & SCX_ENQ_CLEAR_OPSS)
+ atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
+
+ if (is_local) {
+ struct rq *rq = container_of(dsq, struct rq, scx.local_dsq);
+ bool preempt = false;
+
+ if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr &&
+ rq->curr->sched_class == &ext_sched_class) {
+ rq->curr->scx.slice = 0;
+ preempt = true;
+ }
+
+ if (preempt || sched_class_above(&ext_sched_class,
+ rq->curr->sched_class))
+ resched_curr(rq);
+ } else {
+ raw_spin_unlock(&dsq->lock);
+ }
+}
+
+static void task_unlink_from_dsq(struct task_struct *p,
+ struct scx_dispatch_q *dsq)
+{
+ WARN_ON_ONCE(list_empty(&p->scx.dsq_list.node));
+
+ if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) {
+ rb_erase(&p->scx.dsq_priq, &dsq->priq);
+ RB_CLEAR_NODE(&p->scx.dsq_priq);
+ p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ;
+ }
+
+ list_del_init(&p->scx.dsq_list.node);
+ dsq_mod_nr(dsq, -1);
+}
+
+static void dispatch_dequeue(struct rq *rq, struct task_struct *p)
+{
+ struct scx_dispatch_q *dsq = p->scx.dsq;
+ bool is_local = dsq == &rq->scx.local_dsq;
+
+ if (!dsq) {
+ /*
+ * If !dsq && on-list, @p is on @rq's ddsp_deferred_locals.
+ * Unlinking is all that's needed to cancel.
+ */
+ if (unlikely(!list_empty(&p->scx.dsq_list.node)))
+ list_del_init(&p->scx.dsq_list.node);
+
+ /*
+ * When dispatching directly from the BPF scheduler to a local
+ * DSQ, the task isn't associated with any DSQ but
+ * @p->scx.holding_cpu may be set under the protection of
+ * %SCX_OPSS_DISPATCHING.
+ */
+ if (p->scx.holding_cpu >= 0)
+ p->scx.holding_cpu = -1;
+
+ return;
+ }
+
+ if (!is_local)
+ raw_spin_lock(&dsq->lock);
+
+ /*
+ * Now that we hold @dsq->lock, @p->holding_cpu and @p->scx.dsq_* can't
+ * change underneath us.
+ */
+ if (p->scx.holding_cpu < 0) {
+ /* @p must still be on @dsq, dequeue */
+ task_unlink_from_dsq(p, dsq);
+ } else {
+ /*
+ * We're racing against dispatch_to_local_dsq() which already
+ * removed @p from @dsq and set @p->scx.holding_cpu. Clear the
+ * holding_cpu which tells dispatch_to_local_dsq() that it lost
+ * the race.
+ */
+ WARN_ON_ONCE(!list_empty(&p->scx.dsq_list.node));
+ p->scx.holding_cpu = -1;
+ }
+ p->scx.dsq = NULL;
+
+ if (!is_local)
+ raw_spin_unlock(&dsq->lock);
+}
+
+static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id,
+ struct task_struct *p)
+{
+ struct scx_dispatch_q *dsq;
+
+ if (dsq_id == SCX_DSQ_LOCAL)
+ return &rq->scx.local_dsq;
+
+ if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
+ s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
+
+ if (!ops_cpu_valid(cpu, "in SCX_DSQ_LOCAL_ON dispatch verdict"))
+ return find_global_dsq(p);
+
+ return &cpu_rq(cpu)->scx.local_dsq;
+ }
+
+ if (dsq_id == SCX_DSQ_GLOBAL)
+ dsq = find_global_dsq(p);
+ else
+ dsq = find_user_dsq(dsq_id);
+
+ if (unlikely(!dsq)) {
+ scx_ops_error("non-existent DSQ 0x%llx for %s[%d]",
+ dsq_id, p->comm, p->pid);
+ return find_global_dsq(p);
+ }
+
+ return dsq;
+}
+
+static void mark_direct_dispatch(struct task_struct *ddsp_task,
+ struct task_struct *p, u64 dsq_id,
+ u64 enq_flags)
+{
+ /*
+ * Mark that dispatch already happened from ops.select_cpu() or
+ * ops.enqueue() by spoiling direct_dispatch_task with a non-NULL value
+ * which can never match a valid task pointer.
+ */
+ __this_cpu_write(direct_dispatch_task, ERR_PTR(-ESRCH));
+
+ /* @p must match the task on the enqueue path */
+ if (unlikely(p != ddsp_task)) {
+ if (IS_ERR(ddsp_task))
+ scx_ops_error("%s[%d] already direct-dispatched",
+ p->comm, p->pid);
+ else
+ scx_ops_error("scheduling for %s[%d] but trying to direct-dispatch %s[%d]",
+ ddsp_task->comm, ddsp_task->pid,
+ p->comm, p->pid);
+ return;
+ }
+
+ WARN_ON_ONCE(p->scx.ddsp_dsq_id != SCX_DSQ_INVALID);
+ WARN_ON_ONCE(p->scx.ddsp_enq_flags);
+
+ p->scx.ddsp_dsq_id = dsq_id;
+ p->scx.ddsp_enq_flags = enq_flags;
+}
+
+static void direct_dispatch(struct task_struct *p, u64 enq_flags)
+{
+ struct rq *rq = task_rq(p);
+ struct scx_dispatch_q *dsq =
+ find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);
+
+ touch_core_sched_dispatch(rq, p);
+
+ p->scx.ddsp_enq_flags |= enq_flags;
+
+ /*
+ * We are in the enqueue path with @rq locked and pinned, and thus can't
+ * double lock a remote rq and enqueue to its local DSQ. For
+ * DSQ_LOCAL_ON verdicts targeting the local DSQ of a remote CPU, defer
+ * the enqueue so that it's executed when @rq can be unlocked.
+ */
+ if (dsq->id == SCX_DSQ_LOCAL && dsq != &rq->scx.local_dsq) {
+ unsigned long opss;
+
+ opss = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_STATE_MASK;
+
+ switch (opss & SCX_OPSS_STATE_MASK) {
+ case SCX_OPSS_NONE:
+ break;
+ case SCX_OPSS_QUEUEING:
+ /*
+ * As @p was never passed to the BPF side, _release is
+ * not strictly necessary. Still do it for consistency.
+ */
+ atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
+ break;
+ default:
+ WARN_ONCE(true, "sched_ext: %s[%d] has invalid ops state 0x%lx in direct_dispatch()",
+ p->comm, p->pid, opss);
+ atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
+ break;
+ }
+
+ WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
+ list_add_tail(&p->scx.dsq_list.node,
+ &rq->scx.ddsp_deferred_locals);
+ schedule_deferred(rq);
+ return;
+ }
+
+ dispatch_enqueue(dsq, p, p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
+}
+
+static bool scx_rq_online(struct rq *rq)
+{
+ /*
+ * Test both cpu_active() and %SCX_RQ_ONLINE. %SCX_RQ_ONLINE indicates
+ * the online state as seen from the BPF scheduler. cpu_active() test
+ * guarantees that, if this function returns %true, %SCX_RQ_ONLINE will
+ * stay set until the current scheduling operation is complete even if
+ * we aren't locking @rq.
+ */
+ return likely((rq->scx.flags & SCX_RQ_ONLINE) && cpu_active(cpu_of(rq)));
+}
+
+static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
+ int sticky_cpu)
+{
+ struct task_struct **ddsp_taskp;
+ unsigned long qseq;
+
+ WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED));
+
+ /* rq migration */
+ if (sticky_cpu == cpu_of(rq))
+ goto local_norefill;
+
+ /*
+ * If !scx_rq_online(), we already told the BPF scheduler that the CPU
+ * is offline and are just running the hotplug path. Don't bother the
+ * BPF scheduler.
+ */
+ if (!scx_rq_online(rq))
+ goto local;
+
+ if (scx_rq_bypassing(rq)) {
+ if (enq_flags & SCX_ENQ_LAST)
+ goto local;
+ else
+ goto global;
+ }
+
+ if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
+ goto direct;
+
+ /* see %SCX_OPS_ENQ_EXITING */
+ if (!static_branch_unlikely(&scx_ops_enq_exiting) &&
+ unlikely(p->flags & PF_EXITING))
+ goto local;
+
+ /* see %SCX_OPS_ENQ_LAST */
+ if (!static_branch_unlikely(&scx_ops_enq_last) &&
+ (enq_flags & SCX_ENQ_LAST))
+ goto local;
+
+ if (!SCX_HAS_OP(enqueue))
+ goto global;
+
+ /* DSQ bypass didn't trigger, enqueue on the BPF scheduler */
+ qseq = rq->scx.ops_qseq++ << SCX_OPSS_QSEQ_SHIFT;
+
+ WARN_ON_ONCE(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE);
+ atomic_long_set(&p->scx.ops_state, SCX_OPSS_QUEUEING | qseq);
+
+ ddsp_taskp = this_cpu_ptr(&direct_dispatch_task);
+ WARN_ON_ONCE(*ddsp_taskp);
+ *ddsp_taskp = p;
+
+ SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags);
+
+ *ddsp_taskp = NULL;
+ if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
+ goto direct;
+
+ /*
+ * If not directly dispatched, QUEUEING isn't clear yet and dispatch or
+ * dequeue may be waiting. The store_release matches their load_acquire.
+ */
+ atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_QUEUED | qseq);
+ return;
+
+direct:
+ direct_dispatch(p, enq_flags);
+ return;
+
+local:
+ /*
+ * For task-ordering, slice refill must be treated as implying the end
+ * of the current slice. Otherwise, the longer @p stays on the CPU, the
+ * higher priority it becomes from scx_prio_less()'s POV.
+ */
+ touch_core_sched(rq, p);
+ p->scx.slice = SCX_SLICE_DFL;
+local_norefill:
+ dispatch_enqueue(&rq->scx.local_dsq, p, enq_flags);
+ return;
+
+global:
+ touch_core_sched(rq, p); /* see the comment in local: */
+ p->scx.slice = SCX_SLICE_DFL;
+ dispatch_enqueue(find_global_dsq(p), p, enq_flags);
+}
+
+static bool task_runnable(const struct task_struct *p)
+{
+ return !list_empty(&p->scx.runnable_node);
+}
+
+static void set_task_runnable(struct rq *rq, struct task_struct *p)
+{
+ lockdep_assert_rq_held(rq);
+
+ if (p->scx.flags & SCX_TASK_RESET_RUNNABLE_AT) {
+ p->scx.runnable_at = jiffies;
+ p->scx.flags &= ~SCX_TASK_RESET_RUNNABLE_AT;
+ }
+
+ /*
+ * list_add_tail() must be used. scx_ops_bypass() depends on tasks being
+ * appened to the runnable_list.
+ */
+ list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list);
+}
+
+static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
+{
+ list_del_init(&p->scx.runnable_node);
+ if (reset_runnable_at)
+ p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
+}
+
+static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags)
+{
+ int sticky_cpu = p->scx.sticky_cpu;
+
+ if (enq_flags & ENQUEUE_WAKEUP)
+ rq->scx.flags |= SCX_RQ_IN_WAKEUP;
+
+ enq_flags |= rq->scx.extra_enq_flags;
+
+ if (sticky_cpu >= 0)
+ p->scx.sticky_cpu = -1;
+
+ /*
+ * Restoring a running task will be immediately followed by
+ * set_next_task_scx() which expects the task to not be on the BPF
+ * scheduler as tasks can only start running through local DSQs. Force
+ * direct-dispatch into the local DSQ by setting the sticky_cpu.
+ */
+ if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p))
+ sticky_cpu = cpu_of(rq);
+
+ if (p->scx.flags & SCX_TASK_QUEUED) {
+ WARN_ON_ONCE(!task_runnable(p));
+ goto out;
+ }
+
+ set_task_runnable(rq, p);
+ p->scx.flags |= SCX_TASK_QUEUED;
+ rq->scx.nr_running++;
+ add_nr_running(rq, 1);
+
+ if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p))
+ SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags);
+
+ if (enq_flags & SCX_ENQ_WAKEUP)
+ touch_core_sched(rq, p);
+
+ do_enqueue_task(rq, p, enq_flags, sticky_cpu);
+out:
+ rq->scx.flags &= ~SCX_RQ_IN_WAKEUP;
+}
+
+static void ops_dequeue(struct task_struct *p, u64 deq_flags)
+{
+ unsigned long opss;
+
+ /* dequeue is always temporary, don't reset runnable_at */
+ clr_task_runnable(p, false);
+
+ /* acquire ensures that we see the preceding updates on QUEUED */
+ opss = atomic_long_read_acquire(&p->scx.ops_state);
+
+ switch (opss & SCX_OPSS_STATE_MASK) {
+ case SCX_OPSS_NONE:
+ break;
+ case SCX_OPSS_QUEUEING:
+ /*
+ * QUEUEING is started and finished while holding @p's rq lock.
+ * As we're holding the rq lock now, we shouldn't see QUEUEING.
+ */
+ BUG();
+ case SCX_OPSS_QUEUED:
+ if (SCX_HAS_OP(dequeue))
+ SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags);
+
+ if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
+ SCX_OPSS_NONE))
+ break;
+ fallthrough;
+ case SCX_OPSS_DISPATCHING:
+ /*
+ * If @p is being dispatched from the BPF scheduler to a DSQ,
+ * wait for the transfer to complete so that @p doesn't get
+ * added to its DSQ after dequeueing is complete.
+ *
+ * As we're waiting on DISPATCHING with the rq locked, the
+ * dispatching side shouldn't try to lock the rq while
+ * DISPATCHING is set. See dispatch_to_local_dsq().
+ *
+ * DISPATCHING shouldn't have qseq set and control can reach
+ * here with NONE @opss from the above QUEUED case block.
+ * Explicitly wait on %SCX_OPSS_DISPATCHING instead of @opss.
+ */
+ wait_ops_state(p, SCX_OPSS_DISPATCHING);
+ BUG_ON(atomic_long_read(&p->scx.ops_state) != SCX_OPSS_NONE);
+ break;
+ }
+}
+
+static void dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags)
+{
+ if (!(p->scx.flags & SCX_TASK_QUEUED)) {
+ WARN_ON_ONCE(task_runnable(p));
+ return;
+ }
+
+ ops_dequeue(p, deq_flags);
+
+ /*
+ * A currently running task which is going off @rq first gets dequeued
+ * and then stops running. As we want running <-> stopping transitions
+ * to be contained within runnable <-> quiescent transitions, trigger
+ * ->stopping() early here instead of in put_prev_task_scx().
+ *
+ * @p may go through multiple stopping <-> running transitions between
+ * here and put_prev_task_scx() if task attribute changes occur while
+ * balance_scx() leaves @rq unlocked. However, they don't contain any
+ * information meaningful to the BPF scheduler and can be suppressed by
+ * skipping the callbacks if the task is !QUEUED.
+ */
+ if (SCX_HAS_OP(stopping) && task_current(rq, p)) {
+ update_curr_scx(rq);
+ SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false);
+ }
+
+ if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p))
+ SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags);
+
+ if (deq_flags & SCX_DEQ_SLEEP)
+ p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP;
+ else
+ p->scx.flags &= ~SCX_TASK_DEQD_FOR_SLEEP;
+
+ p->scx.flags &= ~SCX_TASK_QUEUED;
+ rq->scx.nr_running--;
+ sub_nr_running(rq, 1);
+
+ dispatch_dequeue(rq, p);
+}
+
+static void yield_task_scx(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ if (SCX_HAS_OP(yield))
+ SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL);
+ else
+ p->scx.slice = 0;
+}
+
+static bool yield_to_task_scx(struct rq *rq, struct task_struct *to)
+{
+ struct task_struct *from = rq->curr;
+
+ if (SCX_HAS_OP(yield))
+ return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to);
+ else
+ return false;
+}
+
+static void move_local_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
+ struct scx_dispatch_q *src_dsq,
+ struct rq *dst_rq)
+{
+ struct scx_dispatch_q *dst_dsq = &dst_rq->scx.local_dsq;
+
+ /* @dsq is locked and @p is on @dst_rq */
+ lockdep_assert_held(&src_dsq->lock);
+ lockdep_assert_rq_held(dst_rq);
+
+ WARN_ON_ONCE(p->scx.holding_cpu >= 0);
+
+ if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT))
+ list_add(&p->scx.dsq_list.node, &dst_dsq->list);
+ else
+ list_add_tail(&p->scx.dsq_list.node, &dst_dsq->list);
+
+ dsq_mod_nr(dst_dsq, 1);
+ p->scx.dsq = dst_dsq;
+}
+
+#ifdef CONFIG_SMP
+/**
+ * move_remote_task_to_local_dsq - Move a task from a foreign rq to a local DSQ
+ * @p: task to move
+ * @enq_flags: %SCX_ENQ_*
+ * @src_rq: rq to move the task from, locked on entry, released on return
+ * @dst_rq: rq to move the task into, locked on return
+ *
+ * Move @p which is currently on @src_rq to @dst_rq's local DSQ.
+ */
+static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
+ struct rq *src_rq, struct rq *dst_rq)
+{
+ lockdep_assert_rq_held(src_rq);
+
+ /* the following marks @p MIGRATING which excludes dequeue */
+ deactivate_task(src_rq, p, 0);
+ set_task_cpu(p, cpu_of(dst_rq));
+ p->scx.sticky_cpu = cpu_of(dst_rq);
+
+ raw_spin_rq_unlock(src_rq);
+ raw_spin_rq_lock(dst_rq);
+
+ /*
+ * We want to pass scx-specific enq_flags but activate_task() will
+ * truncate the upper 32 bit. As we own @rq, we can pass them through
+ * @rq->scx.extra_enq_flags instead.
+ */
+ WARN_ON_ONCE(!cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr));
+ WARN_ON_ONCE(dst_rq->scx.extra_enq_flags);
+ dst_rq->scx.extra_enq_flags = enq_flags;
+ activate_task(dst_rq, p, 0);
+ dst_rq->scx.extra_enq_flags = 0;
+}
+
+/*
+ * Similar to kernel/sched/core.c::is_cpu_allowed(). However, there are two
+ * differences:
+ *
+ * - is_cpu_allowed() asks "Can this task run on this CPU?" while
+ * task_can_run_on_remote_rq() asks "Can the BPF scheduler migrate the task to
+ * this CPU?".
+ *
+ * While migration is disabled, is_cpu_allowed() has to say "yes" as the task
+ * must be allowed to finish on the CPU that it's currently on regardless of
+ * the CPU state. However, task_can_run_on_remote_rq() must say "no" as the
+ * BPF scheduler shouldn't attempt to migrate a task which has migration
+ * disabled.
+ *
+ * - The BPF scheduler is bypassed while the rq is offline and we can always say
+ * no to the BPF scheduler initiated migrations while offline.
+ */
+static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
+ bool trigger_error)
+{
+ int cpu = cpu_of(rq);
+
+ /*
+ * We don't require the BPF scheduler to avoid dispatching to offline
+ * CPUs mostly for convenience but also because CPUs can go offline
+ * between scx_bpf_dispatch() calls and here. Trigger error iff the
+ * picked CPU is outside the allowed mask.
+ */
+ if (!task_allowed_on_cpu(p, cpu)) {
+ if (trigger_error)
+ scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
+ cpu_of(rq), p->comm, p->pid);
+ return false;
+ }
+
+ if (unlikely(is_migration_disabled(p)))
+ return false;
+
+ if (!scx_rq_online(rq))
+ return false;
+
+ return true;
+}
+
+/**
+ * unlink_dsq_and_lock_src_rq() - Unlink task from its DSQ and lock its task_rq
+ * @p: target task
+ * @dsq: locked DSQ @p is currently on
+ * @src_rq: rq @p is currently on, stable with @dsq locked
+ *
+ * Called with @dsq locked but no rq's locked. We want to move @p to a different
+ * DSQ, including any local DSQ, but are not locking @src_rq. Locking @src_rq is
+ * required when transferring into a local DSQ. Even when transferring into a
+ * non-local DSQ, it's better to use the same mechanism to protect against
+ * dequeues and maintain the invariant that @p->scx.dsq can only change while
+ * @src_rq is locked, which e.g. scx_dump_task() depends on.
+ *
+ * We want to grab @src_rq but that can deadlock if we try while locking @dsq,
+ * so we want to unlink @p from @dsq, drop its lock and then lock @src_rq. As
+ * this may race with dequeue, which can't drop the rq lock or fail, do a little
+ * dancing from our side.
+ *
+ * @p->scx.holding_cpu is set to this CPU before @dsq is unlocked. If @p gets
+ * dequeued after we unlock @dsq but before locking @src_rq, the holding_cpu
+ * would be cleared to -1. While other cpus may have updated it to different
+ * values afterwards, as this operation can't be preempted or recurse, the
+ * holding_cpu can never become this CPU again before we're done. Thus, we can
+ * tell whether we lost to dequeue by testing whether the holding_cpu still
+ * points to this CPU. See dispatch_dequeue() for the counterpart.
+ *
+ * On return, @dsq is unlocked and @src_rq is locked. Returns %true if @p is
+ * still valid. %false if lost to dequeue.
+ */
+static bool unlink_dsq_and_lock_src_rq(struct task_struct *p,
+ struct scx_dispatch_q *dsq,
+ struct rq *src_rq)
+{
+ s32 cpu = raw_smp_processor_id();
+
+ lockdep_assert_held(&dsq->lock);
+
+ WARN_ON_ONCE(p->scx.holding_cpu >= 0);
+ task_unlink_from_dsq(p, dsq);
+ p->scx.holding_cpu = cpu;
+
+ raw_spin_unlock(&dsq->lock);
+ raw_spin_rq_lock(src_rq);
+
+ /* task_rq couldn't have changed if we're still the holding cpu */
+ return likely(p->scx.holding_cpu == cpu) &&
+ !WARN_ON_ONCE(src_rq != task_rq(p));
+}
+
+static bool consume_remote_task(struct rq *this_rq, struct task_struct *p,
+ struct scx_dispatch_q *dsq, struct rq *src_rq)
+{
+ raw_spin_rq_unlock(this_rq);
+
+ if (unlink_dsq_and_lock_src_rq(p, dsq, src_rq)) {
+ move_remote_task_to_local_dsq(p, 0, src_rq, this_rq);
+ return true;
+ } else {
+ raw_spin_rq_unlock(src_rq);
+ raw_spin_rq_lock(this_rq);
+ return false;
+ }
+}
+#else /* CONFIG_SMP */
+static inline void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, struct rq *src_rq, struct rq *dst_rq) { WARN_ON_ONCE(1); }
+static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { return false; }
+static inline bool consume_remote_task(struct rq *this_rq, struct task_struct *p, struct scx_dispatch_q *dsq, struct rq *task_rq) { return false; }
+#endif /* CONFIG_SMP */
+
+static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
+{
+ struct task_struct *p;
+retry:
+ /*
+ * The caller can't expect to successfully consume a task if the task's
+ * addition to @dsq isn't guaranteed to be visible somehow. Test
+ * @dsq->list without locking and skip if it seems empty.
+ */
+ if (list_empty(&dsq->list))
+ return false;
+
+ raw_spin_lock(&dsq->lock);
+
+ nldsq_for_each_task(p, dsq) {
+ struct rq *task_rq = task_rq(p);
+
+ if (rq == task_rq) {
+ task_unlink_from_dsq(p, dsq);
+ move_local_task_to_local_dsq(p, 0, dsq, rq);
+ raw_spin_unlock(&dsq->lock);
+ return true;
+ }
+
+ if (task_can_run_on_remote_rq(p, rq, false)) {
+ if (likely(consume_remote_task(rq, p, dsq, task_rq)))
+ return true;
+ goto retry;
+ }
+ }
+
+ raw_spin_unlock(&dsq->lock);
+ return false;
+}
+
+static bool consume_global_dsq(struct rq *rq)
+{
+ int node = cpu_to_node(cpu_of(rq));
+
+ return consume_dispatch_q(rq, global_dsqs[node]);
+}
+
+/**
+ * dispatch_to_local_dsq - Dispatch a task to a local dsq
+ * @rq: current rq which is locked
+ * @dst_dsq: destination DSQ
+ * @p: task to dispatch
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * We're holding @rq lock and want to dispatch @p to @dst_dsq which is a local
+ * DSQ. This function performs all the synchronization dancing needed because
+ * local DSQs are protected with rq locks.
+ *
+ * The caller must have exclusive ownership of @p (e.g. through
+ * %SCX_OPSS_DISPATCHING).
+ */
+static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
+ struct task_struct *p, u64 enq_flags)
+{
+ struct rq *src_rq = task_rq(p);
+ struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
+
+ /*
+ * We're synchronized against dequeue through DISPATCHING. As @p can't
+ * be dequeued, its task_rq and cpus_allowed are stable too.
+ *
+ * If dispatching to @rq that @p is already on, no lock dancing needed.
+ */
+ if (rq == src_rq && rq == dst_rq) {
+ dispatch_enqueue(dst_dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
+ return;
+ }
+
+#ifdef CONFIG_SMP
+ if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) {
+ dispatch_enqueue(find_global_dsq(p), p,
+ enq_flags | SCX_ENQ_CLEAR_OPSS);
+ return;
+ }
+
+ /*
+ * @p is on a possibly remote @src_rq which we need to lock to move the
+ * task. If dequeue is in progress, it'd be locking @src_rq and waiting
+ * on DISPATCHING, so we can't grab @src_rq lock while holding
+ * DISPATCHING.
+ *
+ * As DISPATCHING guarantees that @p is wholly ours, we can pretend that
+ * we're moving from a DSQ and use the same mechanism - mark the task
+ * under transfer with holding_cpu, release DISPATCHING and then follow
+ * the same protocol. See unlink_dsq_and_lock_src_rq().
+ */
+ p->scx.holding_cpu = raw_smp_processor_id();
+
+ /* store_release ensures that dequeue sees the above */
+ atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
+
+ /* switch to @src_rq lock */
+ if (rq != src_rq) {
+ raw_spin_rq_unlock(rq);
+ raw_spin_rq_lock(src_rq);
+ }
+
+ /* task_rq couldn't have changed if we're still the holding cpu */
+ if (likely(p->scx.holding_cpu == raw_smp_processor_id()) &&
+ !WARN_ON_ONCE(src_rq != task_rq(p))) {
+ /*
+ * If @p is staying on the same rq, there's no need to go
+ * through the full deactivate/activate cycle. Optimize by
+ * abbreviating move_remote_task_to_local_dsq().
+ */
+ if (src_rq == dst_rq) {
+ p->scx.holding_cpu = -1;
+ dispatch_enqueue(&dst_rq->scx.local_dsq, p, enq_flags);
+ } else {
+ move_remote_task_to_local_dsq(p, enq_flags,
+ src_rq, dst_rq);
+ }
+
+ /* if the destination CPU is idle, wake it up */
+ if (sched_class_above(p->sched_class, dst_rq->curr->sched_class))
+ resched_curr(dst_rq);
+ }
+
+ /* switch back to @rq lock */
+ if (rq != dst_rq) {
+ raw_spin_rq_unlock(dst_rq);
+ raw_spin_rq_lock(rq);
+ }
+#else /* CONFIG_SMP */
+ BUG(); /* control can not reach here on UP */
+#endif /* CONFIG_SMP */
+}
+
+/**
+ * finish_dispatch - Asynchronously finish dispatching a task
+ * @rq: current rq which is locked
+ * @p: task to finish dispatching
+ * @qseq_at_dispatch: qseq when @p started getting dispatched
+ * @dsq_id: destination DSQ ID
+ * @enq_flags: %SCX_ENQ_*
+ *
+ * Dispatching to local DSQs may need to wait for queueing to complete or
+ * require rq lock dancing. As we don't wanna do either while inside
+ * ops.dispatch() to avoid locking order inversion, we split dispatching into
+ * two parts. scx_bpf_dispatch() which is called by ops.dispatch() records the
+ * task and its qseq. Once ops.dispatch() returns, this function is called to
+ * finish up.
+ *
+ * There is no guarantee that @p is still valid for dispatching or even that it
+ * was valid in the first place. Make sure that the task is still owned by the
+ * BPF scheduler and claim the ownership before dispatching.
+ */
+static void finish_dispatch(struct rq *rq, struct task_struct *p,
+ unsigned long qseq_at_dispatch,
+ u64 dsq_id, u64 enq_flags)
+{
+ struct scx_dispatch_q *dsq;
+ unsigned long opss;
+
+ touch_core_sched_dispatch(rq, p);
+retry:
+ /*
+ * No need for _acquire here. @p is accessed only after a successful
+ * try_cmpxchg to DISPATCHING.
+ */
+ opss = atomic_long_read(&p->scx.ops_state);
+
+ switch (opss & SCX_OPSS_STATE_MASK) {
+ case SCX_OPSS_DISPATCHING:
+ case SCX_OPSS_NONE:
+ /* someone else already got to it */
+ return;
+ case SCX_OPSS_QUEUED:
+ /*
+ * If qseq doesn't match, @p has gone through at least one
+ * dispatch/dequeue and re-enqueue cycle between
+ * scx_bpf_dispatch() and here and we have no claim on it.
+ */
+ if ((opss & SCX_OPSS_QSEQ_MASK) != qseq_at_dispatch)
+ return;
+
+ /*
+ * While we know @p is accessible, we don't yet have a claim on
+ * it - the BPF scheduler is allowed to dispatch tasks
+ * spuriously and there can be a racing dequeue attempt. Let's
+ * claim @p by atomically transitioning it from QUEUED to
+ * DISPATCHING.
+ */
+ if (likely(atomic_long_try_cmpxchg(&p->scx.ops_state, &opss,
+ SCX_OPSS_DISPATCHING)))
+ break;
+ goto retry;
+ case SCX_OPSS_QUEUEING:
+ /*
+ * do_enqueue_task() is in the process of transferring the task
+ * to the BPF scheduler while holding @p's rq lock. As we aren't
+ * holding any kernel or BPF resource that the enqueue path may
+ * depend upon, it's safe to wait.
+ */
+ wait_ops_state(p, opss);
+ goto retry;
+ }
+
+ BUG_ON(!(p->scx.flags & SCX_TASK_QUEUED));
+
+ dsq = find_dsq_for_dispatch(this_rq(), dsq_id, p);
+
+ if (dsq->id == SCX_DSQ_LOCAL)
+ dispatch_to_local_dsq(rq, dsq, p, enq_flags);
+ else
+ dispatch_enqueue(dsq, p, enq_flags | SCX_ENQ_CLEAR_OPSS);
+}
+
+static void flush_dispatch_buf(struct rq *rq)
+{
+ struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
+ u32 u;
+
+ for (u = 0; u < dspc->cursor; u++) {
+ struct scx_dsp_buf_ent *ent = &dspc->buf[u];
+
+ finish_dispatch(rq, ent->task, ent->qseq, ent->dsq_id,
+ ent->enq_flags);
+ }
+
+ dspc->nr_tasks += dspc->cursor;
+ dspc->cursor = 0;
+}
+
+static int balance_one(struct rq *rq, struct task_struct *prev, bool local)
+{
+ struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
+ bool prev_on_scx = prev->sched_class == &ext_sched_class;
+ int nr_loops = SCX_DSP_MAX_LOOPS;
+ bool has_tasks = false;
+
+ lockdep_assert_rq_held(rq);
+ rq->scx.flags |= SCX_RQ_IN_BALANCE;
+
+ if (static_branch_unlikely(&scx_ops_cpu_preempt) &&
+ unlikely(rq->scx.cpu_released)) {
+ /*
+ * If the previous sched_class for the current CPU was not SCX,
+ * notify the BPF scheduler that it again has control of the
+ * core. This callback complements ->cpu_release(), which is
+ * emitted in scx_next_task_picked().
+ */
+ if (SCX_HAS_OP(cpu_acquire))
+ SCX_CALL_OP(0, cpu_acquire, cpu_of(rq), NULL);
+ rq->scx.cpu_released = false;
+ }
+
+ if (prev_on_scx) {
+ WARN_ON_ONCE(local && (prev->scx.flags & SCX_TASK_BAL_KEEP));
+ update_curr_scx(rq);
+
+ /*
+ * If @prev is runnable & has slice left, it has priority and
+ * fetching more just increases latency for the fetched tasks.
+ * Tell put_prev_task_scx() to put @prev on local_dsq. If the
+ * BPF scheduler wants to handle this explicitly, it should
+ * implement ->cpu_released().
+ *
+ * See scx_ops_disable_workfn() for the explanation on the
+ * bypassing test.
+ *
+ * When balancing a remote CPU for core-sched, there won't be a
+ * following put_prev_task_scx() call and we don't own
+ * %SCX_TASK_BAL_KEEP. Instead, pick_task_scx() will test the
+ * same conditions later and pick @rq->curr accordingly.
+ */
+ if ((prev->scx.flags & SCX_TASK_QUEUED) &&
+ prev->scx.slice && !scx_rq_bypassing(rq)) {
+ if (local)
+ prev->scx.flags |= SCX_TASK_BAL_KEEP;
+ goto has_tasks;
+ }
+ }
+
+ /* if there already are tasks to run, nothing to do */
+ if (rq->scx.local_dsq.nr)
+ goto has_tasks;
+
+ if (consume_global_dsq(rq))
+ goto has_tasks;
+
+ if (!SCX_HAS_OP(dispatch) || scx_rq_bypassing(rq) || !scx_rq_online(rq))
+ goto out;
+
+ dspc->rq = rq;
+
+ /*
+ * The dispatch loop. Because flush_dispatch_buf() may drop the rq lock,
+ * the local DSQ might still end up empty after a successful
+ * ops.dispatch(). If the local DSQ is empty even after ops.dispatch()
+ * produced some tasks, retry. The BPF scheduler may depend on this
+ * looping behavior to simplify its implementation.
+ */
+ do {
+ dspc->nr_tasks = 0;
+
+ SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq),
+ prev_on_scx ? prev : NULL);
+
+ flush_dispatch_buf(rq);
+
+ if (rq->scx.local_dsq.nr)
+ goto has_tasks;
+ if (consume_global_dsq(rq))
+ goto has_tasks;
+
+ /*
+ * ops.dispatch() can trap us in this loop by repeatedly
+ * dispatching ineligible tasks. Break out once in a while to
+ * allow the watchdog to run. As IRQ can't be enabled in
+ * balance(), we want to complete this scheduling cycle and then
+ * start a new one. IOW, we want to call resched_curr() on the
+ * next, most likely idle, task, not the current one. Use
+ * scx_bpf_kick_cpu() for deferred kicking.
+ */
+ if (unlikely(!--nr_loops)) {
+ scx_bpf_kick_cpu(cpu_of(rq), 0);
+ break;
+ }
+ } while (dspc->nr_tasks);
+
+ goto out;
+
+has_tasks:
+ has_tasks = true;
+out:
+ rq->scx.flags &= ~SCX_RQ_IN_BALANCE;
+ return has_tasks;
+}
+
+static int balance_scx(struct rq *rq, struct task_struct *prev,
+ struct rq_flags *rf)
+{
+ int ret;
+
+ rq_unpin_lock(rq, rf);
+
+ ret = balance_one(rq, prev, true);
+
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When core-sched is enabled, this ops.balance() call will be followed
+ * by put_prev_scx() and pick_task_scx() on this CPU and pick_task_scx()
+ * on the SMT siblings. Balance the siblings too.
+ */
+ if (sched_core_enabled(rq)) {
+ const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq));
+ int scpu;
+
+ for_each_cpu_andnot(scpu, smt_mask, cpumask_of(cpu_of(rq))) {
+ struct rq *srq = cpu_rq(scpu);
+ struct task_struct *sprev = srq->curr;
+
+ WARN_ON_ONCE(__rq_lockp(rq) != __rq_lockp(srq));
+ update_rq_clock(srq);
+ balance_one(srq, sprev, false);
+ }
+ }
+#endif
+ rq_repin_lock(rq, rf);
+
+ return ret;
+}
+
+static void process_ddsp_deferred_locals(struct rq *rq)
+{
+ struct task_struct *p;
+
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * Now that @rq can be unlocked, execute the deferred enqueueing of
+ * tasks directly dispatched to the local DSQs of other CPUs. See
+ * direct_dispatch(). Keep popping from the head instead of using
+ * list_for_each_entry_safe() as dispatch_local_dsq() may unlock @rq
+ * temporarily.
+ */
+ while ((p = list_first_entry_or_null(&rq->scx.ddsp_deferred_locals,
+ struct task_struct, scx.dsq_list.node))) {
+ struct scx_dispatch_q *dsq;
+
+ list_del_init(&p->scx.dsq_list.node);
+
+ dsq = find_dsq_for_dispatch(rq, p->scx.ddsp_dsq_id, p);
+ if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
+ dispatch_to_local_dsq(rq, dsq, p, p->scx.ddsp_enq_flags);
+ }
+}
+
+static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
+{
+ if (p->scx.flags & SCX_TASK_QUEUED) {
+ /*
+ * Core-sched might decide to execute @p before it is
+ * dispatched. Call ops_dequeue() to notify the BPF scheduler.
+ */
+ ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC);
+ dispatch_dequeue(rq, p);
+ }
+
+ p->se.exec_start = rq_clock_task(rq);
+
+ /* see dequeue_task_scx() on why we skip when !QUEUED */
+ if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED))
+ SCX_CALL_OP_TASK(SCX_KF_REST, running, p);
+
+ clr_task_runnable(p, true);
+
+ /*
+ * @p is getting newly scheduled or got kicked after someone updated its
+ * slice. Refresh whether tick can be stopped. See scx_can_stop_tick().
+ */
+ if ((p->scx.slice == SCX_SLICE_INF) !=
+ (bool)(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
+ if (p->scx.slice == SCX_SLICE_INF)
+ rq->scx.flags |= SCX_RQ_CAN_STOP_TICK;
+ else
+ rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK;
+
+ sched_update_tick_dependency(rq);
+
+ /*
+ * For now, let's refresh the load_avgs just when transitioning
+ * in and out of nohz. In the future, we might want to add a
+ * mechanism which calls the following periodically on
+ * tick-stopped CPUs.
+ */
+ update_other_load_avgs(rq);
+ }
+}
+
+static enum scx_cpu_preempt_reason
+preempt_reason_from_class(const struct sched_class *class)
+{
+#ifdef CONFIG_SMP
+ if (class == &stop_sched_class)
+ return SCX_CPU_PREEMPT_STOP;
+#endif
+ if (class == &dl_sched_class)
+ return SCX_CPU_PREEMPT_DL;
+ if (class == &rt_sched_class)
+ return SCX_CPU_PREEMPT_RT;
+ return SCX_CPU_PREEMPT_UNKNOWN;
+}
+
+static void switch_class_scx(struct rq *rq, struct task_struct *next)
+{
+ const struct sched_class *next_class = next->sched_class;
+
+ if (!scx_enabled())
+ return;
+#ifdef CONFIG_SMP
+ /*
+ * Pairs with the smp_load_acquire() issued by a CPU in
+ * kick_cpus_irq_workfn() who is waiting for this CPU to perform a
+ * resched.
+ */
+ smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
+#endif
+ if (!static_branch_unlikely(&scx_ops_cpu_preempt))
+ return;
+
+ /*
+ * The callback is conceptually meant to convey that the CPU is no
+ * longer under the control of SCX. Therefore, don't invoke the callback
+ * if the next class is below SCX (in which case the BPF scheduler has
+ * actively decided not to schedule any tasks on the CPU).
+ */
+ if (sched_class_above(&ext_sched_class, next_class))
+ return;
+
+ /*
+ * At this point we know that SCX was preempted by a higher priority
+ * sched_class, so invoke the ->cpu_release() callback if we have not
+ * done so already. We only send the callback once between SCX being
+ * preempted, and it regaining control of the CPU.
+ *
+ * ->cpu_release() complements ->cpu_acquire(), which is emitted the
+ * next time that balance_scx() is invoked.
+ */
+ if (!rq->scx.cpu_released) {
+ if (SCX_HAS_OP(cpu_release)) {
+ struct scx_cpu_release_args args = {
+ .reason = preempt_reason_from_class(next_class),
+ .task = next,
+ };
+
+ SCX_CALL_OP(SCX_KF_CPU_RELEASE,
+ cpu_release, cpu_of(rq), &args);
+ }
+ rq->scx.cpu_released = true;
+ }
+}
+
+static void put_prev_task_scx(struct rq *rq, struct task_struct *p)
+{
+ update_curr_scx(rq);
+
+ /* see dequeue_task_scx() on why we skip when !QUEUED */
+ if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED))
+ SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true);
+
+ /*
+ * If we're being called from put_prev_task_balance(), balance_scx() may
+ * have decided that @p should keep running.
+ */
+ if (p->scx.flags & SCX_TASK_BAL_KEEP) {
+ p->scx.flags &= ~SCX_TASK_BAL_KEEP;
+ set_task_runnable(rq, p);
+ dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+ return;
+ }
+
+ if (p->scx.flags & SCX_TASK_QUEUED) {
+ set_task_runnable(rq, p);
+
+ /*
+ * If @p has slice left and balance_scx() didn't tag it for
+ * keeping, @p is getting preempted by a higher priority
+ * scheduler class or core-sched forcing a different task. Leave
+ * it at the head of the local DSQ.
+ */
+ if (p->scx.slice && !scx_rq_bypassing(rq)) {
+ dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD);
+ return;
+ }
+
+ /*
+ * If we're in the pick_next_task path, balance_scx() should
+ * have already populated the local DSQ if there are any other
+ * available tasks. If empty, tell ops.enqueue() that @p is the
+ * only one available for this cpu. ops.enqueue() should put it
+ * on the local DSQ so that the subsequent pick_next_task_scx()
+ * can find the task unless it wants to trigger a separate
+ * follow-up scheduling event.
+ */
+ if (list_empty(&rq->scx.local_dsq.list))
+ do_enqueue_task(rq, p, SCX_ENQ_LAST, -1);
+ else
+ do_enqueue_task(rq, p, 0, -1);
+ }
+}
+
+static struct task_struct *first_local_task(struct rq *rq)
+{
+ return list_first_entry_or_null(&rq->scx.local_dsq.list,
+ struct task_struct, scx.dsq_list.node);
+}
+
+static struct task_struct *pick_next_task_scx(struct rq *rq)
+{
+ struct task_struct *p;
+
+ p = first_local_task(rq);
+ if (!p)
+ return NULL;
+
+ set_next_task_scx(rq, p, true);
+
+ if (unlikely(!p->scx.slice)) {
+ if (!scx_rq_bypassing(rq) && !scx_warned_zero_slice) {
+ printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in pick_next_task_scx()\n",
+ p->comm, p->pid);
+ scx_warned_zero_slice = true;
+ }
+ p->scx.slice = SCX_SLICE_DFL;
+ }
+
+ return p;
+}
+
+#ifdef CONFIG_SCHED_CORE
+/**
+ * scx_prio_less - Task ordering for core-sched
+ * @a: task A
+ * @b: task B
+ *
+ * Core-sched is implemented as an additional scheduling layer on top of the
+ * usual sched_class'es and needs to find out the expected task ordering. For
+ * SCX, core-sched calls this function to interrogate the task ordering.
+ *
+ * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used
+ * to implement the default task ordering. The older the timestamp, the higher
+ * prority the task - the global FIFO ordering matching the default scheduling
+ * behavior.
+ *
+ * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to
+ * implement FIFO ordering within each local DSQ. See pick_task_scx().
+ */
+bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
+ bool in_fi)
+{
+ /*
+ * The const qualifiers are dropped from task_struct pointers when
+ * calling ops.core_sched_before(). Accesses are controlled by the
+ * verifier.
+ */
+ if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a)))
+ return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before,
+ (struct task_struct *)a,
+ (struct task_struct *)b);
+ else
+ return time_after64(a->scx.core_sched_at, b->scx.core_sched_at);
+}
+
+/**
+ * pick_task_scx - Pick a candidate task for core-sched
+ * @rq: rq to pick the candidate task from
+ *
+ * Core-sched calls this function on each SMT sibling to determine the next
+ * tasks to run on the SMT siblings. balance_one() has been called on all
+ * siblings and put_prev_task_scx() has been called only for the current CPU.
+ *
+ * As put_prev_task_scx() hasn't been called on remote CPUs, we can't just look
+ * at the first task in the local dsq. @rq->curr has to be considered explicitly
+ * to mimic %SCX_TASK_BAL_KEEP.
+ */
+static struct task_struct *pick_task_scx(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct task_struct *first = first_local_task(rq);
+
+ if (curr->scx.flags & SCX_TASK_QUEUED) {
+ /* is curr the only runnable task? */
+ if (!first)
+ return curr;
+
+ /*
+ * Does curr trump first? We can always go by core_sched_at for
+ * this comparison as it represents global FIFO ordering when
+ * the default core-sched ordering is used and local-DSQ FIFO
+ * ordering otherwise.
+ *
+ * We can have a task with an earlier timestamp on the DSQ. For
+ * example, when a current task is preempted by a sibling
+ * picking a different cookie, the task would be requeued at the
+ * head of the local DSQ with an earlier timestamp than the
+ * core-sched picked next task. Besides, the BPF scheduler may
+ * dispatch any tasks to the local DSQ anytime.
+ */
+ if (curr->scx.slice && time_before64(curr->scx.core_sched_at,
+ first->scx.core_sched_at))
+ return curr;
+ }
+
+ return first; /* this may be %NULL */
+}
+#endif /* CONFIG_SCHED_CORE */
+
+#ifdef CONFIG_SMP
+
+static bool test_and_clear_cpu_idle(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * SMT mask should be cleared whether we can claim @cpu or not. The SMT
+ * cluster is not wholly idle either way. This also prevents
+ * scx_pick_idle_cpu() from getting caught in an infinite loop.
+ */
+ if (sched_smt_active()) {
+ const struct cpumask *smt = cpu_smt_mask(cpu);
+
+ /*
+ * If offline, @cpu is not its own sibling and
+ * scx_pick_idle_cpu() can get caught in an infinite loop as
+ * @cpu is never cleared from idle_masks.smt. Ensure that @cpu
+ * is eventually cleared.
+ */
+ if (cpumask_intersects(smt, idle_masks.smt))
+ cpumask_andnot(idle_masks.smt, idle_masks.smt, smt);
+ else if (cpumask_test_cpu(cpu, idle_masks.smt))
+ __cpumask_clear_cpu(cpu, idle_masks.smt);
+ }
+#endif
+ return cpumask_test_and_clear_cpu(cpu, idle_masks.cpu);
+}
+
+static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags)
+{
+ int cpu;
+
+retry:
+ if (sched_smt_active()) {
+ cpu = cpumask_any_and_distribute(idle_masks.smt, cpus_allowed);
+ if (cpu < nr_cpu_ids)
+ goto found;
+
+ if (flags & SCX_PICK_IDLE_CORE)
+ return -EBUSY;
+ }
+
+ cpu = cpumask_any_and_distribute(idle_masks.cpu, cpus_allowed);
+ if (cpu >= nr_cpu_ids)
+ return -EBUSY;
+
+found:
+ if (test_and_clear_cpu_idle(cpu))
+ return cpu;
+ else
+ goto retry;
+}
+
+static s32 scx_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
+ u64 wake_flags, bool *found)
+{
+ s32 cpu;
+
+ *found = false;
+
+ /*
+ * If WAKE_SYNC, the waker's local DSQ is empty, and the system is
+ * under utilized, wake up @p to the local DSQ of the waker. Checking
+ * only for an empty local DSQ is insufficient as it could give the
+ * wakee an unfair advantage when the system is oversaturated.
+ * Checking only for the presence of idle CPUs is also insufficient as
+ * the local DSQ of the waker could have tasks piled up on it even if
+ * there is an idle core elsewhere on the system.
+ */
+ cpu = smp_processor_id();
+ if ((wake_flags & SCX_WAKE_SYNC) && p->nr_cpus_allowed > 1 &&
+ !cpumask_empty(idle_masks.cpu) && !(current->flags & PF_EXITING) &&
+ cpu_rq(cpu)->scx.local_dsq.nr == 0) {
+ if (cpumask_test_cpu(cpu, p->cpus_ptr))
+ goto cpu_found;
+ }
+
+ if (p->nr_cpus_allowed == 1) {
+ if (test_and_clear_cpu_idle(prev_cpu)) {
+ cpu = prev_cpu;
+ goto cpu_found;
+ } else {
+ return prev_cpu;
+ }
+ }
+
+ /*
+ * If CPU has SMT, any wholly idle CPU is likely a better pick than
+ * partially idle @prev_cpu.
+ */
+ if (sched_smt_active()) {
+ if (cpumask_test_cpu(prev_cpu, idle_masks.smt) &&
+ test_and_clear_cpu_idle(prev_cpu)) {
+ cpu = prev_cpu;
+ goto cpu_found;
+ }
+
+ cpu = scx_pick_idle_cpu(p->cpus_ptr, SCX_PICK_IDLE_CORE);
+ if (cpu >= 0)
+ goto cpu_found;
+ }
+
+ if (test_and_clear_cpu_idle(prev_cpu)) {
+ cpu = prev_cpu;
+ goto cpu_found;
+ }
+
+ cpu = scx_pick_idle_cpu(p->cpus_ptr, 0);
+ if (cpu >= 0)
+ goto cpu_found;
+
+ return prev_cpu;
+
+cpu_found:
+ *found = true;
+ return cpu;
+}
+
+static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flags)
+{
+ /*
+ * sched_exec() calls with %WF_EXEC when @p is about to exec(2) as it
+ * can be a good migration opportunity with low cache and memory
+ * footprint. Returning a CPU different than @prev_cpu triggers
+ * immediate rq migration. However, for SCX, as the current rq
+ * association doesn't dictate where the task is going to run, this
+ * doesn't fit well. If necessary, we can later add a dedicated method
+ * which can decide to preempt self to force it through the regular
+ * scheduling path.
+ */
+ if (unlikely(wake_flags & WF_EXEC))
+ return prev_cpu;
+
+ if (SCX_HAS_OP(select_cpu) && !scx_rq_bypassing(task_rq(p))) {
+ s32 cpu;
+ struct task_struct **ddsp_taskp;
+
+ ddsp_taskp = this_cpu_ptr(&direct_dispatch_task);
+ WARN_ON_ONCE(*ddsp_taskp);
+ *ddsp_taskp = p;
+
+ cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU,
+ select_cpu, p, prev_cpu, wake_flags);
+ *ddsp_taskp = NULL;
+ if (ops_cpu_valid(cpu, "from ops.select_cpu()"))
+ return cpu;
+ else
+ return prev_cpu;
+ } else {
+ bool found;
+ s32 cpu;
+
+ cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, &found);
+ if (found) {
+ p->scx.slice = SCX_SLICE_DFL;
+ p->scx.ddsp_dsq_id = SCX_DSQ_LOCAL;
+ }
+ return cpu;
+ }
+}
+
+static void task_woken_scx(struct rq *rq, struct task_struct *p)
+{
+ run_deferred(rq);
+}
+
+static void set_cpus_allowed_scx(struct task_struct *p,
+ struct affinity_context *ac)
+{
+ set_cpus_allowed_common(p, ac);
+
+ /*
+ * The effective cpumask is stored in @p->cpus_ptr which may temporarily
+ * differ from the configured one in @p->cpus_mask. Always tell the bpf
+ * scheduler the effective one.
+ *
+ * Fine-grained memory write control is enforced by BPF making the const
+ * designation pointless. Cast it away when calling the operation.
+ */
+ if (SCX_HAS_OP(set_cpumask))
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
+ (struct cpumask *)p->cpus_ptr);
+}
+
+static void reset_idle_masks(void)
+{
+ /*
+ * Consider all online cpus idle. Should converge to the actual state
+ * quickly.
+ */
+ cpumask_copy(idle_masks.cpu, cpu_online_mask);
+ cpumask_copy(idle_masks.smt, cpu_online_mask);
+}
+
+void __scx_update_idle(struct rq *rq, bool idle)
+{
+ int cpu = cpu_of(rq);
+
+ if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) {
+ SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle);
+ if (!static_branch_unlikely(&scx_builtin_idle_enabled))
+ return;
+ }
+
+ if (idle)
+ cpumask_set_cpu(cpu, idle_masks.cpu);
+ else
+ cpumask_clear_cpu(cpu, idle_masks.cpu);
+
+#ifdef CONFIG_SCHED_SMT
+ if (sched_smt_active()) {
+ const struct cpumask *smt = cpu_smt_mask(cpu);
+
+ if (idle) {
+ /*
+ * idle_masks.smt handling is racy but that's fine as
+ * it's only for optimization and self-correcting.
+ */
+ for_each_cpu(cpu, smt) {
+ if (!cpumask_test_cpu(cpu, idle_masks.cpu))
+ return;
+ }
+ cpumask_or(idle_masks.smt, idle_masks.smt, smt);
+ } else {
+ cpumask_andnot(idle_masks.smt, idle_masks.smt, smt);
+ }
+ }
+#endif
+}
+
+static void handle_hotplug(struct rq *rq, bool online)
+{
+ int cpu = cpu_of(rq);
+
+ atomic_long_inc(&scx_hotplug_seq);
+
+ if (online && SCX_HAS_OP(cpu_online))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu);
+ else if (!online && SCX_HAS_OP(cpu_offline))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu);
+ else
+ scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
+ "cpu %d going %s, exiting scheduler", cpu,
+ online ? "online" : "offline");
+}
+
+void scx_rq_activate(struct rq *rq)
+{
+ handle_hotplug(rq, true);
+}
+
+void scx_rq_deactivate(struct rq *rq)
+{
+ handle_hotplug(rq, false);
+}
+
+static void rq_online_scx(struct rq *rq)
+{
+ rq->scx.flags |= SCX_RQ_ONLINE;
+}
+
+static void rq_offline_scx(struct rq *rq)
+{
+ rq->scx.flags &= ~SCX_RQ_ONLINE;
+}
+
+#else /* CONFIG_SMP */
+
+static bool test_and_clear_cpu_idle(int cpu) { return false; }
+static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) { return -EBUSY; }
+static void reset_idle_masks(void) {}
+
+#endif /* CONFIG_SMP */
+
+static bool check_rq_for_timeouts(struct rq *rq)
+{
+ struct task_struct *p;
+ struct rq_flags rf;
+ bool timed_out = false;
+
+ rq_lock_irqsave(rq, &rf);
+ list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) {
+ unsigned long last_runnable = p->scx.runnable_at;
+
+ if (unlikely(time_after(jiffies,
+ last_runnable + scx_watchdog_timeout))) {
+ u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable);
+
+ scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
+ "%s[%d] failed to run for %u.%03us",
+ p->comm, p->pid,
+ dur_ms / 1000, dur_ms % 1000);
+ timed_out = true;
+ break;
+ }
+ }
+ rq_unlock_irqrestore(rq, &rf);
+
+ return timed_out;
+}
+
+static void scx_watchdog_workfn(struct work_struct *work)
+{
+ int cpu;
+
+ WRITE_ONCE(scx_watchdog_timestamp, jiffies);
+
+ for_each_online_cpu(cpu) {
+ if (unlikely(check_rq_for_timeouts(cpu_rq(cpu))))
+ break;
+
+ cond_resched();
+ }
+ queue_delayed_work(system_unbound_wq, to_delayed_work(work),
+ scx_watchdog_timeout / 2);
+}
+
+void scx_tick(struct rq *rq)
+{
+ unsigned long last_check;
+
+ if (!scx_enabled())
+ return;
+
+ last_check = READ_ONCE(scx_watchdog_timestamp);
+ if (unlikely(time_after(jiffies,
+ last_check + READ_ONCE(scx_watchdog_timeout)))) {
+ u32 dur_ms = jiffies_to_msecs(jiffies - last_check);
+
+ scx_ops_error_kind(SCX_EXIT_ERROR_STALL,
+ "watchdog failed to check in for %u.%03us",
+ dur_ms / 1000, dur_ms % 1000);
+ }
+
+ update_other_load_avgs(rq);
+}
+
+static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
+{
+ update_curr_scx(rq);
+
+ /*
+ * While disabling, always resched and refresh core-sched timestamp as
+ * we can't trust the slice management or ops.core_sched_before().
+ */
+ if (scx_rq_bypassing(rq)) {
+ curr->scx.slice = 0;
+ touch_core_sched(rq, curr);
+ } else if (SCX_HAS_OP(tick)) {
+ SCX_CALL_OP(SCX_KF_REST, tick, curr);
+ }
+
+ if (!curr->scx.slice)
+ resched_curr(rq);
+}
+
+#ifdef CONFIG_EXT_GROUP_SCHED
+static struct cgroup *tg_cgrp(struct task_group *tg)
+{
+ /*
+ * If CGROUP_SCHED is disabled, @tg is NULL. If @tg is an autogroup,
+ * @tg->css.cgroup is NULL. In both cases, @tg can be treated as the
+ * root cgroup.
+ */
+ if (tg && tg->css.cgroup)
+ return tg->css.cgroup;
+ else
+ return &cgrp_dfl_root.cgrp;
+}
+
+#define SCX_INIT_TASK_ARGS_CGROUP(tg) .cgroup = tg_cgrp(tg),
+
+#else /* CONFIG_EXT_GROUP_SCHED */
+
+#define SCX_INIT_TASK_ARGS_CGROUP(tg)
+
+#endif /* CONFIG_EXT_GROUP_SCHED */
+
+static enum scx_task_state scx_get_task_state(const struct task_struct *p)
+{
+ return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT;
+}
+
+static void scx_set_task_state(struct task_struct *p, enum scx_task_state state)
+{
+ enum scx_task_state prev_state = scx_get_task_state(p);
+ bool warn = false;
+
+ BUILD_BUG_ON(SCX_TASK_NR_STATES > (1 << SCX_TASK_STATE_BITS));
+
+ switch (state) {
+ case SCX_TASK_NONE:
+ break;
+ case SCX_TASK_INIT:
+ warn = prev_state != SCX_TASK_NONE;
+ break;
+ case SCX_TASK_READY:
+ warn = prev_state == SCX_TASK_NONE;
+ break;
+ case SCX_TASK_ENABLED:
+ warn = prev_state != SCX_TASK_READY;
+ break;
+ default:
+ warn = true;
+ return;
+ }
+
+ WARN_ONCE(warn, "sched_ext: Invalid task state transition %d -> %d for %s[%d]",
+ prev_state, state, p->comm, p->pid);
+
+ p->scx.flags &= ~SCX_TASK_STATE_MASK;
+ p->scx.flags |= state << SCX_TASK_STATE_SHIFT;
+}
+
+static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool fork)
+{
+ int ret;
+
+ p->scx.disallow = false;
+
+ if (SCX_HAS_OP(init_task)) {
+ struct scx_init_task_args args = {
+ SCX_INIT_TASK_ARGS_CGROUP(tg)
+ .fork = fork,
+ };
+
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args);
+ if (unlikely(ret)) {
+ ret = ops_sanitize_err("init_task", ret);
+ return ret;
+ }
+ }
+
+ scx_set_task_state(p, SCX_TASK_INIT);
+
+ if (p->scx.disallow) {
+ if (!fork) {
+ struct rq *rq;
+ struct rq_flags rf;
+
+ rq = task_rq_lock(p, &rf);
+
+ /*
+ * We're in the load path and @p->policy will be applied
+ * right after. Reverting @p->policy here and rejecting
+ * %SCHED_EXT transitions from scx_check_setscheduler()
+ * guarantees that if ops.init_task() sets @p->disallow,
+ * @p can never be in SCX.
+ */
+ if (p->policy == SCHED_EXT) {
+ p->policy = SCHED_NORMAL;
+ atomic_long_inc(&scx_nr_rejected);
+ }
+
+ task_rq_unlock(rq, p, &rf);
+ } else if (p->policy == SCHED_EXT) {
+ scx_ops_error("ops.init_task() set task->scx.disallow for %s[%d] during fork",
+ p->comm, p->pid);
+ }
+ }
+
+ p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
+ return 0;
+}
+
+static void scx_ops_enable_task(struct task_struct *p)
+{
+ u32 weight;
+
+ lockdep_assert_rq_held(task_rq(p));
+
+ /*
+ * Set the weight before calling ops.enable() so that the scheduler
+ * doesn't see a stale value if they inspect the task struct.
+ */
+ if (task_has_idle_policy(p))
+ weight = WEIGHT_IDLEPRIO;
+ else
+ weight = sched_prio_to_weight[p->static_prio - MAX_RT_PRIO];
+
+ p->scx.weight = sched_weight_to_cgroup(weight);
+
+ if (SCX_HAS_OP(enable))
+ SCX_CALL_OP_TASK(SCX_KF_REST, enable, p);
+ scx_set_task_state(p, SCX_TASK_ENABLED);
+
+ if (SCX_HAS_OP(set_weight))
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+}
+
+static void scx_ops_disable_task(struct task_struct *p)
+{
+ lockdep_assert_rq_held(task_rq(p));
+ WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
+
+ if (SCX_HAS_OP(disable))
+ SCX_CALL_OP(SCX_KF_REST, disable, p);
+ scx_set_task_state(p, SCX_TASK_READY);
+}
+
+static void scx_ops_exit_task(struct task_struct *p)
+{
+ struct scx_exit_task_args args = {
+ .cancelled = false,
+ };
+
+ lockdep_assert_rq_held(task_rq(p));
+
+ switch (scx_get_task_state(p)) {
+ case SCX_TASK_NONE:
+ return;
+ case SCX_TASK_INIT:
+ args.cancelled = true;
+ break;
+ case SCX_TASK_READY:
+ break;
+ case SCX_TASK_ENABLED:
+ scx_ops_disable_task(p);
+ break;
+ default:
+ WARN_ON_ONCE(true);
+ return;
+ }
+
+ if (SCX_HAS_OP(exit_task))
+ SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args);
+ scx_set_task_state(p, SCX_TASK_NONE);
+}
+
+void init_scx_entity(struct sched_ext_entity *scx)
+{
+ /*
+ * init_idle() calls this function again after fork sequence is
+ * complete. Don't touch ->tasks_node as it's already linked.
+ */
+ memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node));
+
+ INIT_LIST_HEAD(&scx->dsq_list.node);
+ RB_CLEAR_NODE(&scx->dsq_priq);
+ scx->sticky_cpu = -1;
+ scx->holding_cpu = -1;
+ INIT_LIST_HEAD(&scx->runnable_node);
+ scx->runnable_at = jiffies;
+ scx->ddsp_dsq_id = SCX_DSQ_INVALID;
+ scx->slice = SCX_SLICE_DFL;
+}
+
+void scx_pre_fork(struct task_struct *p)
+{
+ /*
+ * BPF scheduler enable/disable paths want to be able to iterate and
+ * update all tasks which can become complex when racing forks. As
+ * enable/disable are very cold paths, let's use a percpu_rwsem to
+ * exclude forks.
+ */
+ percpu_down_read(&scx_fork_rwsem);
+}
+
+int scx_fork(struct task_struct *p)
+{
+ percpu_rwsem_assert_held(&scx_fork_rwsem);
+
+ if (scx_ops_init_task_enabled)
+ return scx_ops_init_task(p, task_group(p), true);
+ else
+ return 0;
+}
+
+void scx_post_fork(struct task_struct *p)
+{
+ if (scx_ops_init_task_enabled) {
+ scx_set_task_state(p, SCX_TASK_READY);
+
+ /*
+ * Enable the task immediately if it's running on sched_ext.
+ * Otherwise, it'll be enabled in switching_to_scx() if and
+ * when it's ever configured to run with a SCHED_EXT policy.
+ */
+ if (p->sched_class == &ext_sched_class) {
+ struct rq_flags rf;
+ struct rq *rq;
+
+ rq = task_rq_lock(p, &rf);
+ scx_ops_enable_task(p);
+ task_rq_unlock(rq, p, &rf);
+ }
+ }
+
+ spin_lock_irq(&scx_tasks_lock);
+ list_add_tail(&p->scx.tasks_node, &scx_tasks);
+ spin_unlock_irq(&scx_tasks_lock);
+
+ percpu_up_read(&scx_fork_rwsem);
+}
+
+void scx_cancel_fork(struct task_struct *p)
+{
+ if (scx_enabled()) {
+ struct rq *rq;
+ struct rq_flags rf;
+
+ rq = task_rq_lock(p, &rf);
+ WARN_ON_ONCE(scx_get_task_state(p) >= SCX_TASK_READY);
+ scx_ops_exit_task(p);
+ task_rq_unlock(rq, p, &rf);
+ }
+
+ percpu_up_read(&scx_fork_rwsem);
+}
+
+void sched_ext_free(struct task_struct *p)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&scx_tasks_lock, flags);
+ list_del_init(&p->scx.tasks_node);
+ spin_unlock_irqrestore(&scx_tasks_lock, flags);
+
+ /*
+ * @p is off scx_tasks and wholly ours. scx_ops_enable()'s READY ->
+ * ENABLED transitions can't race us. Disable ops for @p.
+ */
+ if (scx_get_task_state(p) != SCX_TASK_NONE) {
+ struct rq_flags rf;
+ struct rq *rq;
+
+ rq = task_rq_lock(p, &rf);
+ scx_ops_exit_task(p);
+ task_rq_unlock(rq, p, &rf);
+ }
+}
+
+static void reweight_task_scx(struct rq *rq, struct task_struct *p,
+ const struct load_weight *lw)
+{
+ lockdep_assert_rq_held(task_rq(p));
+
+ p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight));
+ if (SCX_HAS_OP(set_weight))
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
+}
+
+static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio)
+{
+}
+
+static void switching_to_scx(struct rq *rq, struct task_struct *p)
+{
+ scx_ops_enable_task(p);
+
+ /*
+ * set_cpus_allowed_scx() is not called while @p is associated with a
+ * different scheduler class. Keep the BPF scheduler up-to-date.
+ */
+ if (SCX_HAS_OP(set_cpumask))
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p,
+ (struct cpumask *)p->cpus_ptr);
+}
+
+static void switched_from_scx(struct rq *rq, struct task_struct *p)
+{
+ scx_ops_disable_task(p);
+}
+
+static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
+static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
+
+int scx_check_setscheduler(struct task_struct *p, int policy)
+{
+ lockdep_assert_rq_held(task_rq(p));
+
+ /* if disallow, reject transitioning into SCX */
+ if (scx_enabled() && READ_ONCE(p->scx.disallow) &&
+ p->policy != policy && policy == SCHED_EXT)
+ return -EACCES;
+
+ return 0;
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+bool scx_can_stop_tick(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ if (scx_rq_bypassing(rq))
+ return false;
+
+ if (p->sched_class != &ext_sched_class)
+ return true;
+
+ /*
+ * @rq can dispatch from different DSQs, so we can't tell whether it
+ * needs the tick or not by looking at nr_running. Allow stopping ticks
+ * iff the BPF scheduler indicated so. See set_next_task_scx().
+ */
+ return rq->scx.flags & SCX_RQ_CAN_STOP_TICK;
+}
+#endif
+
+#ifdef CONFIG_EXT_GROUP_SCHED
+
+DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
+static bool scx_cgroup_enabled;
+static bool cgroup_warned_missing_weight;
+static bool cgroup_warned_missing_idle;
+
+static void scx_cgroup_warn_missing_weight(struct task_group *tg)
+{
+ if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
+ cgroup_warned_missing_weight)
+ return;
+
+ if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
+ return;
+
+ pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
+ scx_ops.name);
+ cgroup_warned_missing_weight = true;
+}
+
+static void scx_cgroup_warn_missing_idle(struct task_group *tg)
+{
+ if (!scx_cgroup_enabled || cgroup_warned_missing_idle)
+ return;
+
+ if (!tg->idle)
+ return;
+
+ pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
+ scx_ops.name);
+ cgroup_warned_missing_idle = true;
+}
+
+int scx_tg_online(struct task_group *tg)
+{
+ int ret = 0;
+
+ WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));
+
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ scx_cgroup_warn_missing_weight(tg);
+
+ if (scx_cgroup_enabled) {
+ if (SCX_HAS_OP(cgroup_init)) {
+ struct scx_cgroup_init_args args =
+ { .weight = tg->scx_weight };
+
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ tg->css.cgroup, &args);
+ if (ret)
+ ret = ops_sanitize_err("cgroup_init", ret);
+ }
+ if (ret == 0)
+ tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
+ } else {
+ tg->scx_flags |= SCX_TG_ONLINE;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+ return ret;
+}
+
+void scx_tg_offline(struct task_group *tg)
+{
+ WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE));
+
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
+ tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
+
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+int scx_cgroup_can_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+ struct task_struct *p;
+ int ret;
+
+ /* released in scx_finish/cancel_attach() */
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (!scx_cgroup_enabled)
+ return 0;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ struct cgroup *from = tg_cgrp(task_group(p));
+ struct cgroup *to = tg_cgrp(css_tg(css));
+
+ WARN_ON_ONCE(p->scx.cgrp_moving_from);
+
+ /*
+ * sched_move_task() omits identity migrations. Let's match the
+ * behavior so that ops.cgroup_prep_move() and ops.cgroup_move()
+ * always match one-to-one.
+ */
+ if (from == to)
+ continue;
+
+ if (SCX_HAS_OP(cgroup_prep_move)) {
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
+ p, from, css->cgroup);
+ if (ret)
+ goto err;
+ }
+
+ p->scx.cgrp_moving_from = from;
+ }
+
+ return 0;
+
+err:
+ cgroup_taskset_for_each(p, css, tset) {
+ if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
+ p->scx.cgrp_moving_from, css->cgroup);
+ p->scx.cgrp_moving_from = NULL;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+ return ops_sanitize_err("cgroup_prep_move", ret);
+}
+
+void scx_move_task(struct task_struct *p)
+{
+ if (!scx_cgroup_enabled)
+ return;
+
+ /*
+ * We're called from sched_move_task() which handles both cgroup and
+ * autogroup moves. Ignore the latter.
+ *
+ * Also ignore exiting tasks, because in the exit path tasks transition
+ * from the autogroup to the root group, so task_group_is_autogroup()
+ * alone isn't able to catch exiting autogroup tasks. This is safe for
+ * cgroup_move(), because cgroup migrations never happen for PF_EXITING
+ * tasks.
+ */
+ if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING))
+ return;
+
+ /*
+ * @p must have ops.cgroup_prep_move() called on it and thus
+ * cgrp_moving_from set.
+ */
+ if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
+ SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
+ p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
+ p->scx.cgrp_moving_from = NULL;
+}
+
+void scx_cgroup_finish_attach(void)
+{
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+ struct task_struct *p;
+
+ if (!scx_cgroup_enabled)
+ goto out_unlock;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
+ p->scx.cgrp_moving_from, css->cgroup);
+ p->scx.cgrp_moving_from = NULL;
+ }
+out_unlock:
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_group_set_weight(struct task_group *tg, unsigned long weight)
+{
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (scx_cgroup_enabled && tg->scx_weight != weight) {
+ if (SCX_HAS_OP(cgroup_set_weight))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
+ tg_cgrp(tg), weight);
+ tg->scx_weight = weight;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_group_set_idle(struct task_group *tg, bool idle)
+{
+ percpu_down_read(&scx_cgroup_rwsem);
+ scx_cgroup_warn_missing_idle(tg);
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+static void scx_cgroup_lock(void)
+{
+ percpu_down_write(&scx_cgroup_rwsem);
+}
+
+static void scx_cgroup_unlock(void)
+{
+ percpu_up_write(&scx_cgroup_rwsem);
+}
+
+#else /* CONFIG_EXT_GROUP_SCHED */
+
+static inline void scx_cgroup_lock(void) {}
+static inline void scx_cgroup_unlock(void) {}
+
+#endif /* CONFIG_EXT_GROUP_SCHED */
+
+/*
+ * Omitted operations:
+ *
+ * - wakeup_preempt: NOOP as it isn't useful in the wakeup path because the task
+ * isn't tied to the CPU at that point. Preemption is implemented by resetting
+ * the victim task's slice to 0 and triggering reschedule on the target CPU.
+ *
+ * - migrate_task_rq: Unnecessary as task to cpu mapping is transient.
+ *
+ * - task_fork/dead: We need fork/dead notifications for all tasks regardless of
+ * their current sched_class. Call them directly from sched core instead.
+ */
+DEFINE_SCHED_CLASS(ext) = {
+ .enqueue_task = enqueue_task_scx,
+ .dequeue_task = dequeue_task_scx,
+ .yield_task = yield_task_scx,
+ .yield_to_task = yield_to_task_scx,
+
+ .wakeup_preempt = wakeup_preempt_scx,
+
+ .balance = balance_scx,
+ .pick_next_task = pick_next_task_scx,
+
+ .put_prev_task = put_prev_task_scx,
+ .set_next_task = set_next_task_scx,
+
+ .switch_class = switch_class_scx,
+
+#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_scx,
+ .task_woken = task_woken_scx,
+ .set_cpus_allowed = set_cpus_allowed_scx,
+
+ .rq_online = rq_online_scx,
+ .rq_offline = rq_offline_scx,
+#endif
+
+#ifdef CONFIG_SCHED_CORE
+ .pick_task = pick_task_scx,
+#endif
+
+ .task_tick = task_tick_scx,
+
+ .switching_to = switching_to_scx,
+ .switched_from = switched_from_scx,
+ .switched_to = switched_to_scx,
+ .reweight_task = reweight_task_scx,
+ .prio_changed = prio_changed_scx,
+
+ .update_curr = update_curr_scx,
+
+#ifdef CONFIG_UCLAMP_TASK
+ .uclamp_enabled = 1,
+#endif
+};
+
+static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id)
+{
+ memset(dsq, 0, sizeof(*dsq));
+
+ raw_spin_lock_init(&dsq->lock);
+ INIT_LIST_HEAD(&dsq->list);
+ dsq->id = dsq_id;
+}
+
+static struct scx_dispatch_q *create_dsq(u64 dsq_id, int node)
+{
+ struct scx_dispatch_q *dsq;
+ int ret;
+
+ if (dsq_id & SCX_DSQ_FLAG_BUILTIN)
+ return ERR_PTR(-EINVAL);
+
+ dsq = kmalloc_node(sizeof(*dsq), GFP_KERNEL, node);
+ if (!dsq)
+ return ERR_PTR(-ENOMEM);
+
+ init_dsq(dsq, dsq_id);
+
+ ret = rhashtable_insert_fast(&dsq_hash, &dsq->hash_node,
+ dsq_hash_params);
+ if (ret) {
+ kfree(dsq);
+ return ERR_PTR(ret);
+ }
+ return dsq;
+}
+
+static void free_dsq_irq_workfn(struct irq_work *irq_work)
+{
+ struct llist_node *to_free = llist_del_all(&dsqs_to_free);
+ struct scx_dispatch_q *dsq, *tmp_dsq;
+
+ llist_for_each_entry_safe(dsq, tmp_dsq, to_free, free_node)
+ kfree_rcu(dsq, rcu);
+}
+
+static DEFINE_IRQ_WORK(free_dsq_irq_work, free_dsq_irq_workfn);
+
+static void destroy_dsq(u64 dsq_id)
+{
+ struct scx_dispatch_q *dsq;
+ unsigned long flags;
+
+ rcu_read_lock();
+
+ dsq = find_user_dsq(dsq_id);
+ if (!dsq)
+ goto out_unlock_rcu;
+
+ raw_spin_lock_irqsave(&dsq->lock, flags);
+
+ if (dsq->nr) {
+ scx_ops_error("attempting to destroy in-use dsq 0x%016llx (nr=%u)",
+ dsq->id, dsq->nr);
+ goto out_unlock_dsq;
+ }
+
+ if (rhashtable_remove_fast(&dsq_hash, &dsq->hash_node, dsq_hash_params))
+ goto out_unlock_dsq;
+
+ /*
+ * Mark dead by invalidating ->id to prevent dispatch_enqueue() from
+ * queueing more tasks. As this function can be called from anywhere,
+ * freeing is bounced through an irq work to avoid nesting RCU
+ * operations inside scheduler locks.
+ */
+ dsq->id = SCX_DSQ_INVALID;
+ llist_add(&dsq->free_node, &dsqs_to_free);
+ irq_work_queue(&free_dsq_irq_work);
+
+out_unlock_dsq:
+ raw_spin_unlock_irqrestore(&dsq->lock, flags);
+out_unlock_rcu:
+ rcu_read_unlock();
+}
+
+#ifdef CONFIG_EXT_GROUP_SCHED
+static void scx_cgroup_exit(void)
+{
+ struct cgroup_subsys_state *css;
+
+ percpu_rwsem_assert_held(&scx_cgroup_rwsem);
+
+ WARN_ON_ONCE(!scx_cgroup_enabled);
+ scx_cgroup_enabled = false;
+
+ /*
+ * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
+ * cgroups and exit all the inited ones, all online cgroups are exited.
+ */
+ rcu_read_lock();
+ css_for_each_descendant_post(css, &root_task_group.css) {
+ struct task_group *tg = css_tg(css);
+
+ if (!(tg->scx_flags & SCX_TG_INITED))
+ continue;
+ tg->scx_flags &= ~SCX_TG_INITED;
+
+ if (!scx_ops.cgroup_exit)
+ continue;
+
+ if (WARN_ON_ONCE(!css_tryget(css)))
+ continue;
+ rcu_read_unlock();
+
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);
+
+ rcu_read_lock();
+ css_put(css);
+ }
+ rcu_read_unlock();
+}
+
+static int scx_cgroup_init(void)
+{
+ struct cgroup_subsys_state *css;
+ int ret;
+
+ percpu_rwsem_assert_held(&scx_cgroup_rwsem);
+
+ cgroup_warned_missing_weight = false;
+ cgroup_warned_missing_idle = false;
+
+ /*
+ * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk
+ * cgroups and init, all online cgroups are initialized.
+ */
+ rcu_read_lock();
+ css_for_each_descendant_pre(css, &root_task_group.css) {
+ struct task_group *tg = css_tg(css);
+ struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
+
+ scx_cgroup_warn_missing_weight(tg);
+ scx_cgroup_warn_missing_idle(tg);
+
+ if ((tg->scx_flags &
+ (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
+ continue;
+
+ if (!scx_ops.cgroup_init) {
+ tg->scx_flags |= SCX_TG_INITED;
+ continue;
+ }
+
+ if (WARN_ON_ONCE(!css_tryget(css)))
+ continue;
+ rcu_read_unlock();
+
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ css->cgroup, &args);
+ if (ret) {
+ css_put(css);
+ return ret;
+ }
+ tg->scx_flags |= SCX_TG_INITED;
+
+ rcu_read_lock();
+ css_put(css);
+ }
+ rcu_read_unlock();
+
+ WARN_ON_ONCE(scx_cgroup_enabled);
+ scx_cgroup_enabled = true;
+
+ return 0;
+}
+
+#else
+static void scx_cgroup_exit(void) {}
+static int scx_cgroup_init(void) { return 0; }
+#endif
+
+
+/********************************************************************************
+ * Sysfs interface and ops enable/disable.
+ */
+
+#define SCX_ATTR(_name) \
+ static struct kobj_attribute scx_attr_##_name = { \
+ .attr = { .name = __stringify(_name), .mode = 0444 }, \
+ .show = scx_attr_##_name##_show, \
+ }
+
+static ssize_t scx_attr_state_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%s\n",
+ scx_ops_enable_state_str[scx_ops_enable_state()]);
+}
+SCX_ATTR(state);
+
+static ssize_t scx_attr_switch_all_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", READ_ONCE(scx_switching_all));
+}
+SCX_ATTR(switch_all);
+
+static ssize_t scx_attr_nr_rejected_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_nr_rejected));
+}
+SCX_ATTR(nr_rejected);
+
+static ssize_t scx_attr_hotplug_seq_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_hotplug_seq));
+}
+SCX_ATTR(hotplug_seq);
+
+static ssize_t scx_attr_enable_seq_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_enable_seq));
+}
+SCX_ATTR(enable_seq);
+
+static struct attribute *scx_global_attrs[] = {
+ &scx_attr_state.attr,
+ &scx_attr_switch_all.attr,
+ &scx_attr_nr_rejected.attr,
+ &scx_attr_hotplug_seq.attr,
+ &scx_attr_enable_seq.attr,
+ NULL,
+};
+
+static const struct attribute_group scx_global_attr_group = {
+ .attrs = scx_global_attrs,
+};
+
+static void scx_kobj_release(struct kobject *kobj)
+{
+ kfree(kobj);
+}
+
+static ssize_t scx_attr_ops_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ return sysfs_emit(buf, "%s\n", scx_ops.name);
+}
+SCX_ATTR(ops);
+
+static struct attribute *scx_sched_attrs[] = {
+ &scx_attr_ops.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(scx_sched);
+
+static const struct kobj_type scx_ktype = {
+ .release = scx_kobj_release,
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = scx_sched_groups,
+};
+
+static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
+{
+ return add_uevent_var(env, "SCXOPS=%s", scx_ops.name);
+}
+
+static const struct kset_uevent_ops scx_uevent_ops = {
+ .uevent = scx_uevent,
+};
+
+/*
+ * Used by sched_fork() and __setscheduler_prio() to pick the matching
+ * sched_class. dl/rt are already handled.
+ */
+bool task_should_scx(struct task_struct *p)
+{
+ if (!scx_enabled() ||
+ unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING))
+ return false;
+ if (READ_ONCE(scx_switching_all))
+ return true;
+ return p->policy == SCHED_EXT;
+}
+
+/**
+ * scx_ops_bypass - [Un]bypass scx_ops and guarantee forward progress
+ *
+ * Bypassing guarantees that all runnable tasks make forward progress without
+ * trusting the BPF scheduler. We can't grab any mutexes or rwsems as they might
+ * be held by tasks that the BPF scheduler is forgetting to run, which
+ * unfortunately also excludes toggling the static branches.
+ *
+ * Let's work around by overriding a couple ops and modifying behaviors based on
+ * the DISABLING state and then cycling the queued tasks through dequeue/enqueue
+ * to force global FIFO scheduling.
+ *
+ * - ops.select_cpu() is ignored and the default select_cpu() is used.
+ *
+ * - ops.enqueue() is ignored and tasks are queued in simple global FIFO order.
+ *
+ * - ops.dispatch() is ignored.
+ *
+ * - balance_scx() does not set %SCX_RQ_BAL_KEEP on no*n-zero slice as slice
+ * can't be trusted. Whenever a tick triggers, the running task is rotated to
+ * the tail of the queue with core_sched_at touched.
+ *
+ * - pick_next_task() suppresses zero slice warning.
+ *
+ * - scx_bpf_kick_cpu() is disabled to avoid irq_work malfunction during PM
+ * operations.
+ *
+ * - scx_prio_less() reverts to the default core_sched_at order.
+ */
+static void scx_ops_bypass(bool bypass)
+{
+ int depth, cpu;
+
+ if (bypass) {
+ depth = atomic_inc_return(&scx_ops_bypass_depth);
+ WARN_ON_ONCE(depth <= 0);
+ if (depth != 1)
+ return;
+ } else {
+ depth = atomic_dec_return(&scx_ops_bypass_depth);
+ WARN_ON_ONCE(depth < 0);
+ if (depth != 0)
+ return;
+ }
+
+ /*
+ * No task property is changing. We just need to make sure all currently
+ * queued tasks are re-queued according to the new scx_rq_bypassing()
+ * state. As an optimization, walk each rq's runnable_list instead of
+ * the scx_tasks list.
+ *
+ * This function can't trust the scheduler and thus can't use
+ * cpus_read_lock(). Walk all possible CPUs instead of online.
+ */
+ for_each_possible_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ struct rq_flags rf;
+ struct task_struct *p, *n;
+
+ rq_lock_irqsave(rq, &rf);
+
+ if (bypass) {
+ WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING);
+ rq->scx.flags |= SCX_RQ_BYPASSING;
+ } else {
+ WARN_ON_ONCE(!(rq->scx.flags & SCX_RQ_BYPASSING));
+ rq->scx.flags &= ~SCX_RQ_BYPASSING;
+ }
+
+ /*
+ * We need to guarantee that no tasks are on the BPF scheduler
+ * while bypassing. Either we see enabled or the enable path
+ * sees scx_rq_bypassing() before moving tasks to SCX.
+ */
+ if (!scx_enabled()) {
+ rq_unlock_irqrestore(rq, &rf);
+ continue;
+ }
+
+ /*
+ * The use of list_for_each_entry_safe_reverse() is required
+ * because each task is going to be removed from and added back
+ * to the runnable_list during iteration. Because they're added
+ * to the tail of the list, safe reverse iteration can still
+ * visit all nodes.
+ */
+ list_for_each_entry_safe_reverse(p, n, &rq->scx.runnable_list,
+ scx.runnable_node) {
+ struct sched_enq_and_set_ctx ctx;
+
+ /* cycling deq/enq is enough, see the function comment */
+ sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
+ sched_enq_and_set_task(&ctx);
+ }
+
+ rq_unlock_irqrestore(rq, &rf);
+
+ /* resched to restore ticks and idle state */
+ resched_cpu(cpu);
+ }
+}
+
+static void free_exit_info(struct scx_exit_info *ei)
+{
+ kfree(ei->dump);
+ kfree(ei->msg);
+ kfree(ei->bt);
+ kfree(ei);
+}
+
+static struct scx_exit_info *alloc_exit_info(size_t exit_dump_len)
+{
+ struct scx_exit_info *ei;
+
+ ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+ if (!ei)
+ return NULL;
+
+ ei->bt = kcalloc(SCX_EXIT_BT_LEN, sizeof(ei->bt[0]), GFP_KERNEL);
+ ei->msg = kzalloc(SCX_EXIT_MSG_LEN, GFP_KERNEL);
+ ei->dump = kzalloc(exit_dump_len, GFP_KERNEL);
+
+ if (!ei->bt || !ei->msg || !ei->dump) {
+ free_exit_info(ei);
+ return NULL;
+ }
+
+ return ei;
+}
+
+static const char *scx_exit_reason(enum scx_exit_kind kind)
+{
+ switch (kind) {
+ case SCX_EXIT_UNREG:
+ return "unregistered from user space";
+ case SCX_EXIT_UNREG_BPF:
+ return "unregistered from BPF";
+ case SCX_EXIT_UNREG_KERN:
+ return "unregistered from the main kernel";
+ case SCX_EXIT_SYSRQ:
+ return "disabled by sysrq-S";
+ case SCX_EXIT_ERROR:
+ return "runtime error";
+ case SCX_EXIT_ERROR_BPF:
+ return "scx_bpf_error";
+ case SCX_EXIT_ERROR_STALL:
+ return "runnable task stall";
+ default:
+ return "<UNKNOWN>";
+ }
+}
+
+static void scx_ops_disable_workfn(struct kthread_work *work)
+{
+ struct scx_exit_info *ei = scx_exit_info;
+ struct scx_task_iter sti;
+ struct task_struct *p;
+ struct rhashtable_iter rht_iter;
+ struct scx_dispatch_q *dsq;
+ int i, kind;
+
+ kind = atomic_read(&scx_exit_kind);
+ while (true) {
+ /*
+ * NONE indicates that a new scx_ops has been registered since
+ * disable was scheduled - don't kill the new ops. DONE
+ * indicates that the ops has already been disabled.
+ */
+ if (kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE)
+ return;
+ if (atomic_try_cmpxchg(&scx_exit_kind, &kind, SCX_EXIT_DONE))
+ break;
+ }
+ ei->kind = kind;
+ ei->reason = scx_exit_reason(ei->kind);
+
+ /* guarantee forward progress by bypassing scx_ops */
+ scx_ops_bypass(true);
+
+ switch (scx_ops_set_enable_state(SCX_OPS_DISABLING)) {
+ case SCX_OPS_DISABLING:
+ WARN_ONCE(true, "sched_ext: duplicate disabling instance?");
+ break;
+ case SCX_OPS_DISABLED:
+ pr_warn("sched_ext: ops error detected without ops (%s)\n",
+ scx_exit_info->msg);
+ WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
+ SCX_OPS_DISABLING);
+ goto done;
+ default:
+ break;
+ }
+
+ /*
+ * Here, every runnable task is guaranteed to make forward progress and
+ * we can safely use blocking synchronization constructs. Actually
+ * disable ops.
+ */
+ mutex_lock(&scx_ops_enable_mutex);
+
+ static_branch_disable(&__scx_switched_all);
+ WRITE_ONCE(scx_switching_all, false);
+
+ /*
+ * Shut down cgroup support before tasks so that the cgroup attach path
+ * doesn't race against scx_ops_exit_task().
+ */
+ scx_cgroup_lock();
+ scx_cgroup_exit();
+ scx_cgroup_unlock();
+
+ /*
+ * The BPF scheduler is going away. All tasks including %TASK_DEAD ones
+ * must be switched out and exited synchronously.
+ */
+ percpu_down_write(&scx_fork_rwsem);
+
+ scx_ops_init_task_enabled = false;
+
+ scx_task_iter_start(&sti);
+ while ((p = scx_task_iter_next_locked(&sti))) {
+ const struct sched_class *old_class = p->sched_class;
+ struct sched_enq_and_set_ctx ctx;
+
+ sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
+
+ __setscheduler_prio(p, p->prio);
+ check_class_changing(task_rq(p), p, old_class);
+
+ sched_enq_and_set_task(&ctx);
+
+ check_class_changed(task_rq(p), p, old_class, p->prio);
+ scx_ops_exit_task(p);
+ }
+ scx_task_iter_stop(&sti);
+ percpu_up_write(&scx_fork_rwsem);
+
+ /* no task is on scx, turn off all the switches and flush in-progress calls */
+ static_branch_disable(&__scx_ops_enabled);
+ for (i = SCX_OPI_BEGIN; i < SCX_OPI_END; i++)
+ static_branch_disable(&scx_has_op[i]);
+ static_branch_disable(&scx_ops_enq_last);
+ static_branch_disable(&scx_ops_enq_exiting);
+ static_branch_disable(&scx_ops_cpu_preempt);
+ static_branch_disable(&scx_builtin_idle_enabled);
+ synchronize_rcu();
+
+ if (ei->kind >= SCX_EXIT_ERROR) {
+ pr_err("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
+ scx_ops.name, ei->reason);
+
+ if (ei->msg[0] != '\0')
+ pr_err("sched_ext: %s: %s\n", scx_ops.name, ei->msg);
+#ifdef CONFIG_STACKTRACE
+ stack_trace_print(ei->bt, ei->bt_len, 2);
+#endif
+ } else {
+ pr_info("sched_ext: BPF scheduler \"%s\" disabled (%s)\n",
+ scx_ops.name, ei->reason);
+ }
+
+ if (scx_ops.exit)
+ SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei);
+
+ cancel_delayed_work_sync(&scx_watchdog_work);
+
+ /*
+ * Delete the kobject from the hierarchy eagerly in addition to just
+ * dropping a reference. Otherwise, if the object is deleted
+ * asynchronously, sysfs could observe an object of the same name still
+ * in the hierarchy when another scheduler is loaded.
+ */
+ kobject_del(scx_root_kobj);
+ kobject_put(scx_root_kobj);
+ scx_root_kobj = NULL;
+
+ memset(&scx_ops, 0, sizeof(scx_ops));
+
+ rhashtable_walk_enter(&dsq_hash, &rht_iter);
+ do {
+ rhashtable_walk_start(&rht_iter);
+
+ while ((dsq = rhashtable_walk_next(&rht_iter)) && !IS_ERR(dsq))
+ destroy_dsq(dsq->id);
+
+ rhashtable_walk_stop(&rht_iter);
+ } while (dsq == ERR_PTR(-EAGAIN));
+ rhashtable_walk_exit(&rht_iter);
+
+ free_percpu(scx_dsp_ctx);
+ scx_dsp_ctx = NULL;
+ scx_dsp_max_batch = 0;
+
+ free_exit_info(scx_exit_info);
+ scx_exit_info = NULL;
+
+ mutex_unlock(&scx_ops_enable_mutex);
+
+ WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_DISABLED) !=
+ SCX_OPS_DISABLING);
+done:
+ scx_ops_bypass(false);
+}
+
+static DEFINE_KTHREAD_WORK(scx_ops_disable_work, scx_ops_disable_workfn);
+
+static void schedule_scx_ops_disable_work(void)
+{
+ struct kthread_worker *helper = READ_ONCE(scx_ops_helper);
+
+ /*
+ * We may be called spuriously before the first bpf_sched_ext_reg(). If
+ * scx_ops_helper isn't set up yet, there's nothing to do.
+ */
+ if (helper)
+ kthread_queue_work(helper, &scx_ops_disable_work);
+}
+
+static void scx_ops_disable(enum scx_exit_kind kind)
+{
+ int none = SCX_EXIT_NONE;
+
+ if (WARN_ON_ONCE(kind == SCX_EXIT_NONE || kind == SCX_EXIT_DONE))
+ kind = SCX_EXIT_ERROR;
+
+ atomic_try_cmpxchg(&scx_exit_kind, &none, kind);
+
+ schedule_scx_ops_disable_work();
+}
+
+static void dump_newline(struct seq_buf *s)
+{
+ trace_sched_ext_dump("");
+
+ /* @s may be zero sized and seq_buf triggers WARN if so */
+ if (s->size)
+ seq_buf_putc(s, '\n');
+}
+
+static __printf(2, 3) void dump_line(struct seq_buf *s, const char *fmt, ...)
+{
+ va_list args;
+
+#ifdef CONFIG_TRACEPOINTS
+ if (trace_sched_ext_dump_enabled()) {
+ /* protected by scx_dump_state()::dump_lock */
+ static char line_buf[SCX_EXIT_MSG_LEN];
+
+ va_start(args, fmt);
+ vscnprintf(line_buf, sizeof(line_buf), fmt, args);
+ va_end(args);
+
+ trace_sched_ext_dump(line_buf);
+ }
+#endif
+ /* @s may be zero sized and seq_buf triggers WARN if so */
+ if (s->size) {
+ va_start(args, fmt);
+ seq_buf_vprintf(s, fmt, args);
+ va_end(args);
+
+ seq_buf_putc(s, '\n');
+ }
+}
+
+static void dump_stack_trace(struct seq_buf *s, const char *prefix,
+ const unsigned long *bt, unsigned int len)
+{
+ unsigned int i;
+
+ for (i = 0; i < len; i++)
+ dump_line(s, "%s%pS", prefix, (void *)bt[i]);
+}
+
+static void ops_dump_init(struct seq_buf *s, const char *prefix)
+{
+ struct scx_dump_data *dd = &scx_dump_data;
+
+ lockdep_assert_irqs_disabled();
+
+ dd->cpu = smp_processor_id(); /* allow scx_bpf_dump() */
+ dd->first = true;
+ dd->cursor = 0;
+ dd->s = s;
+ dd->prefix = prefix;
+}
+
+static void ops_dump_flush(void)
+{
+ struct scx_dump_data *dd = &scx_dump_data;
+ char *line = dd->buf.line;
+
+ if (!dd->cursor)
+ return;
+
+ /*
+ * There's something to flush and this is the first line. Insert a blank
+ * line to distinguish ops dump.
+ */
+ if (dd->first) {
+ dump_newline(dd->s);
+ dd->first = false;
+ }
+
+ /*
+ * There may be multiple lines in $line. Scan and emit each line
+ * separately.
+ */
+ while (true) {
+ char *end = line;
+ char c;
+
+ while (*end != '\n' && *end != '\0')
+ end++;
+
+ /*
+ * If $line overflowed, it may not have newline at the end.
+ * Always emit with a newline.
+ */
+ c = *end;
+ *end = '\0';
+ dump_line(dd->s, "%s%s", dd->prefix, line);
+ if (c == '\0')
+ break;
+
+ /* move to the next line */
+ end++;
+ if (*end == '\0')
+ break;
+ line = end;
+ }
+
+ dd->cursor = 0;
+}
+
+static void ops_dump_exit(void)
+{
+ ops_dump_flush();
+ scx_dump_data.cpu = -1;
+}
+
+static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx,
+ struct task_struct *p, char marker)
+{
+ static unsigned long bt[SCX_EXIT_BT_LEN];
+ char dsq_id_buf[19] = "(n/a)";
+ unsigned long ops_state = atomic_long_read(&p->scx.ops_state);
+ unsigned int bt_len = 0;
+
+ if (p->scx.dsq)
+ scnprintf(dsq_id_buf, sizeof(dsq_id_buf), "0x%llx",
+ (unsigned long long)p->scx.dsq->id);
+
+ dump_newline(s);
+ dump_line(s, " %c%c %s[%d] %+ldms",
+ marker, task_state_to_char(p), p->comm, p->pid,
+ jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies));
+ dump_line(s, " scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu",
+ scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK,
+ p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK,
+ ops_state >> SCX_OPSS_QSEQ_SHIFT);
+ dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu",
+ p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf,
+ p->scx.dsq_vtime);
+ dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr));
+
+ if (SCX_HAS_OP(dump_task)) {
+ ops_dump_init(s, " ");
+ SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p);
+ ops_dump_exit();
+ }
+
+#ifdef CONFIG_STACKTRACE
+ bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1);
+#endif
+ if (bt_len) {
+ dump_newline(s);
+ dump_stack_trace(s, " ", bt, bt_len);
+ }
+}
+
+static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
+{
+ static DEFINE_SPINLOCK(dump_lock);
+ static const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n";
+ struct scx_dump_ctx dctx = {
+ .kind = ei->kind,
+ .exit_code = ei->exit_code,
+ .reason = ei->reason,
+ .at_ns = ktime_get_ns(),
+ .at_jiffies = jiffies,
+ };
+ struct seq_buf s;
+ unsigned long flags;
+ char *buf;
+ int cpu;
+
+ spin_lock_irqsave(&dump_lock, flags);
+
+ seq_buf_init(&s, ei->dump, dump_len);
+
+ if (ei->kind == SCX_EXIT_NONE) {
+ dump_line(&s, "Debug dump triggered by %s", ei->reason);
+ } else {
+ dump_line(&s, "%s[%d] triggered exit kind %d:",
+ current->comm, current->pid, ei->kind);
+ dump_line(&s, " %s (%s)", ei->reason, ei->msg);
+ dump_newline(&s);
+ dump_line(&s, "Backtrace:");
+ dump_stack_trace(&s, " ", ei->bt, ei->bt_len);
+ }
+
+ if (SCX_HAS_OP(dump)) {
+ ops_dump_init(&s, "");
+ SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx);
+ ops_dump_exit();
+ }
+
+ dump_newline(&s);
+ dump_line(&s, "CPU states");
+ dump_line(&s, "----------");
+
+ for_each_possible_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ struct rq_flags rf;
+ struct task_struct *p;
+ struct seq_buf ns;
+ size_t avail, used;
+ bool idle;
+
+ rq_lock(rq, &rf);
+
+ idle = list_empty(&rq->scx.runnable_list) &&
+ rq->curr->sched_class == &idle_sched_class;
+
+ if (idle && !SCX_HAS_OP(dump_cpu))
+ goto next;
+
+ /*
+ * We don't yet know whether ops.dump_cpu() will produce output
+ * and we may want to skip the default CPU dump if it doesn't.
+ * Use a nested seq_buf to generate the standard dump so that we
+ * can decide whether to commit later.
+ */
+ avail = seq_buf_get_buf(&s, &buf);
+ seq_buf_init(&ns, buf, avail);
+
+ dump_newline(&ns);
+ dump_line(&ns, "CPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu",
+ cpu, rq->scx.nr_running, rq->scx.flags,
+ rq->scx.cpu_released, rq->scx.ops_qseq,
+ rq->scx.pnt_seq);
+ dump_line(&ns, " curr=%s[%d] class=%ps",
+ rq->curr->comm, rq->curr->pid,
+ rq->curr->sched_class);
+ if (!cpumask_empty(rq->scx.cpus_to_kick))
+ dump_line(&ns, " cpus_to_kick : %*pb",
+ cpumask_pr_args(rq->scx.cpus_to_kick));
+ if (!cpumask_empty(rq->scx.cpus_to_kick_if_idle))
+ dump_line(&ns, " idle_to_kick : %*pb",
+ cpumask_pr_args(rq->scx.cpus_to_kick_if_idle));
+ if (!cpumask_empty(rq->scx.cpus_to_preempt))
+ dump_line(&ns, " cpus_to_preempt: %*pb",
+ cpumask_pr_args(rq->scx.cpus_to_preempt));
+ if (!cpumask_empty(rq->scx.cpus_to_wait))
+ dump_line(&ns, " cpus_to_wait : %*pb",
+ cpumask_pr_args(rq->scx.cpus_to_wait));
+
+ used = seq_buf_used(&ns);
+ if (SCX_HAS_OP(dump_cpu)) {
+ ops_dump_init(&ns, " ");
+ SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle);
+ ops_dump_exit();
+ }
+
+ /*
+ * If idle && nothing generated by ops.dump_cpu(), there's
+ * nothing interesting. Skip.
+ */
+ if (idle && used == seq_buf_used(&ns))
+ goto next;
+
+ /*
+ * $s may already have overflowed when $ns was created. If so,
+ * calling commit on it will trigger BUG.
+ */
+ if (avail) {
+ seq_buf_commit(&s, seq_buf_used(&ns));
+ if (seq_buf_has_overflowed(&ns))
+ seq_buf_set_overflow(&s);
+ }
+
+ if (rq->curr->sched_class == &ext_sched_class)
+ scx_dump_task(&s, &dctx, rq->curr, '*');
+
+ list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node)
+ scx_dump_task(&s, &dctx, p, ' ');
+ next:
+ rq_unlock(rq, &rf);
+ }
+
+ if (seq_buf_has_overflowed(&s) && dump_len >= sizeof(trunc_marker))
+ memcpy(ei->dump + dump_len - sizeof(trunc_marker),
+ trunc_marker, sizeof(trunc_marker));
+
+ spin_unlock_irqrestore(&dump_lock, flags);
+}
+
+static void scx_ops_error_irq_workfn(struct irq_work *irq_work)
+{
+ struct scx_exit_info *ei = scx_exit_info;
+
+ if (ei->kind >= SCX_EXIT_ERROR)
+ scx_dump_state(ei, scx_ops.exit_dump_len);
+
+ schedule_scx_ops_disable_work();
+}
+
+static DEFINE_IRQ_WORK(scx_ops_error_irq_work, scx_ops_error_irq_workfn);
+
+static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind,
+ s64 exit_code,
+ const char *fmt, ...)
+{
+ struct scx_exit_info *ei = scx_exit_info;
+ int none = SCX_EXIT_NONE;
+ va_list args;
+
+ if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind))
+ return;
+
+ ei->exit_code = exit_code;
+#ifdef CONFIG_STACKTRACE
+ if (kind >= SCX_EXIT_ERROR)
+ ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1);
+#endif
+ va_start(args, fmt);
+ vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args);
+ va_end(args);
+
+ /*
+ * Set ei->kind and ->reason for scx_dump_state(). They'll be set again
+ * in scx_ops_disable_workfn().
+ */
+ ei->kind = kind;
+ ei->reason = scx_exit_reason(ei->kind);
+
+ irq_work_queue(&scx_ops_error_irq_work);
+}
+
+static struct kthread_worker *scx_create_rt_helper(const char *name)
+{
+ struct kthread_worker *helper;
+
+ helper = kthread_create_worker(0, name);
+ if (helper)
+ sched_set_fifo(helper->task);
+ return helper;
+}
+
+static void check_hotplug_seq(const struct sched_ext_ops *ops)
+{
+ unsigned long long global_hotplug_seq;
+
+ /*
+ * If a hotplug event has occurred between when a scheduler was
+ * initialized, and when we were able to attach, exit and notify user
+ * space about it.
+ */
+ if (ops->hotplug_seq) {
+ global_hotplug_seq = atomic_long_read(&scx_hotplug_seq);
+ if (ops->hotplug_seq != global_hotplug_seq) {
+ scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG,
+ "expected hotplug seq %llu did not match actual %llu",
+ ops->hotplug_seq, global_hotplug_seq);
+ }
+ }
+}
+
+static int validate_ops(const struct sched_ext_ops *ops)
+{
+ /*
+ * It doesn't make sense to specify the SCX_OPS_ENQ_LAST flag if the
+ * ops.enqueue() callback isn't implemented.
+ */
+ if ((ops->flags & SCX_OPS_ENQ_LAST) && !ops->enqueue) {
+ scx_ops_error("SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
+{
+ struct scx_task_iter sti;
+ struct task_struct *p;
+ unsigned long timeout;
+ int i, cpu, node, ret;
+
+ if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN),
+ cpu_possible_mask)) {
+ pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation");
+ return -EINVAL;
+ }
+
+ mutex_lock(&scx_ops_enable_mutex);
+
+ if (!scx_ops_helper) {
+ WRITE_ONCE(scx_ops_helper,
+ scx_create_rt_helper("sched_ext_ops_helper"));
+ if (!scx_ops_helper) {
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
+ }
+
+ if (!global_dsqs) {
+ struct scx_dispatch_q **dsqs;
+
+ dsqs = kcalloc(nr_node_ids, sizeof(dsqs[0]), GFP_KERNEL);
+ if (!dsqs) {
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
+
+ for_each_node_state(node, N_POSSIBLE) {
+ struct scx_dispatch_q *dsq;
+
+ dsq = kzalloc_node(sizeof(*dsq), GFP_KERNEL, node);
+ if (!dsq) {
+ for_each_node_state(node, N_POSSIBLE)
+ kfree(dsqs[node]);
+ kfree(dsqs);
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
+
+ init_dsq(dsq, SCX_DSQ_GLOBAL);
+ dsqs[node] = dsq;
+ }
+
+ global_dsqs = dsqs;
+ }
+
+ if (scx_ops_enable_state() != SCX_OPS_DISABLED) {
+ ret = -EBUSY;
+ goto err_unlock;
+ }
+
+ scx_root_kobj = kzalloc(sizeof(*scx_root_kobj), GFP_KERNEL);
+ if (!scx_root_kobj) {
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
+
+ scx_root_kobj->kset = scx_kset;
+ ret = kobject_init_and_add(scx_root_kobj, &scx_ktype, NULL, "root");
+ if (ret < 0)
+ goto err;
+
+ scx_exit_info = alloc_exit_info(ops->exit_dump_len);
+ if (!scx_exit_info) {
+ ret = -ENOMEM;
+ goto err_del;
+ }
+
+ /*
+ * Set scx_ops, transition to ENABLING and clear exit info to arm the
+ * disable path. Failure triggers full disabling from here on.
+ */
+ scx_ops = *ops;
+
+ WARN_ON_ONCE(scx_ops_set_enable_state(SCX_OPS_ENABLING) !=
+ SCX_OPS_DISABLED);
+
+ atomic_set(&scx_exit_kind, SCX_EXIT_NONE);
+ scx_warned_zero_slice = false;
+
+ atomic_long_set(&scx_nr_rejected, 0);
+
+ for_each_possible_cpu(cpu)
+ cpu_rq(cpu)->scx.cpuperf_target = SCX_CPUPERF_ONE;
+
+ /*
+ * Keep CPUs stable during enable so that the BPF scheduler can track
+ * online CPUs by watching ->on/offline_cpu() after ->init().
+ */
+ cpus_read_lock();
+
+ if (scx_ops.init) {
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init);
+ if (ret) {
+ ret = ops_sanitize_err("init", ret);
+ cpus_read_unlock();
+ goto err_disable;
+ }
+ }
+
+ for (i = SCX_OPI_CPU_HOTPLUG_BEGIN; i < SCX_OPI_CPU_HOTPLUG_END; i++)
+ if (((void (**)(void))ops)[i])
+ static_branch_enable_cpuslocked(&scx_has_op[i]);
+
+ check_hotplug_seq(ops);
+ cpus_read_unlock();
+
+ ret = validate_ops(ops);
+ if (ret)
+ goto err_disable;
+
+ WARN_ON_ONCE(scx_dsp_ctx);
+ scx_dsp_max_batch = ops->dispatch_max_batch ?: SCX_DSP_DFL_MAX_BATCH;
+ scx_dsp_ctx = __alloc_percpu(struct_size_t(struct scx_dsp_ctx, buf,
+ scx_dsp_max_batch),
+ __alignof__(struct scx_dsp_ctx));
+ if (!scx_dsp_ctx) {
+ ret = -ENOMEM;
+ goto err_disable;
+ }
+
+ if (ops->timeout_ms)
+ timeout = msecs_to_jiffies(ops->timeout_ms);
+ else
+ timeout = SCX_WATCHDOG_MAX_TIMEOUT;
+
+ WRITE_ONCE(scx_watchdog_timeout, timeout);
+ WRITE_ONCE(scx_watchdog_timestamp, jiffies);
+ queue_delayed_work(system_unbound_wq, &scx_watchdog_work,
+ scx_watchdog_timeout / 2);
+
+ /*
+ * Once __scx_ops_enabled is set, %current can be switched to SCX
+ * anytime. This can lead to stalls as some BPF schedulers (e.g.
+ * userspace scheduling) may not function correctly before all tasks are
+ * switched. Init in bypass mode to guarantee forward progress.
+ */
+ scx_ops_bypass(true);
+
+ for (i = SCX_OPI_NORMAL_BEGIN; i < SCX_OPI_NORMAL_END; i++)
+ if (((void (**)(void))ops)[i])
+ static_branch_enable(&scx_has_op[i]);
+
+ if (ops->flags & SCX_OPS_ENQ_LAST)
+ static_branch_enable(&scx_ops_enq_last);
+
+ if (ops->flags & SCX_OPS_ENQ_EXITING)
+ static_branch_enable(&scx_ops_enq_exiting);
+ if (scx_ops.cpu_acquire || scx_ops.cpu_release)
+ static_branch_enable(&scx_ops_cpu_preempt);
+
+ if (!ops->update_idle || (ops->flags & SCX_OPS_KEEP_BUILTIN_IDLE)) {
+ reset_idle_masks();
+ static_branch_enable(&scx_builtin_idle_enabled);
+ } else {
+ static_branch_disable(&scx_builtin_idle_enabled);
+ }
+
+ /*
+ * Lock out forks, cgroup on/offlining and moves before opening the
+ * floodgate so that they don't wander into the operations prematurely.
+ */
+ percpu_down_write(&scx_fork_rwsem);
+
+ WARN_ON_ONCE(scx_ops_init_task_enabled);
+ scx_ops_init_task_enabled = true;
+
+ /*
+ * Enable ops for every task. Fork is excluded by scx_fork_rwsem
+ * preventing new tasks from being added. No need to exclude tasks
+ * leaving as sched_ext_free() can handle both prepped and enabled
+ * tasks. Prep all tasks first and then enable them with preemption
+ * disabled.
+ *
+ * All cgroups should be initialized before scx_ops_init_task() so that
+ * the BPF scheduler can reliably track each task's cgroup membership
+ * from scx_ops_init_task(). Lock out cgroup on/offlining and task
+ * migrations while tasks are being initialized so that
+ * scx_cgroup_can_attach() never sees uninitialized tasks.
+ */
+ scx_cgroup_lock();
+ ret = scx_cgroup_init();
+ if (ret)
+ goto err_disable_unlock_all;
+
+ scx_task_iter_start(&sti);
+ while ((p = scx_task_iter_next_locked(&sti))) {
+ /*
+ * @p may already be dead, have lost all its usages counts and
+ * be waiting for RCU grace period before being freed. @p can't
+ * be initialized for SCX in such cases and should be ignored.
+ */
+ if (!tryget_task_struct(p))
+ continue;
+
+ scx_task_iter_unlock(&sti);
+
+ ret = scx_ops_init_task(p, task_group(p), false);
+ if (ret) {
+ put_task_struct(p);
+ scx_task_iter_relock(&sti);
+ scx_task_iter_stop(&sti);
+ pr_err("sched_ext: ops.init_task() failed (%d) for %s[%d] while loading\n",
+ ret, p->comm, p->pid);
+ goto err_disable_unlock_all;
+ }
+
+ scx_set_task_state(p, SCX_TASK_READY);
+
+ put_task_struct(p);
+ scx_task_iter_relock(&sti);
+ }
+ scx_task_iter_stop(&sti);
+ scx_cgroup_unlock();
+ percpu_up_write(&scx_fork_rwsem);
+
+ /*
+ * All tasks are READY. It's safe to turn on scx_enabled() and switch
+ * all eligible tasks.
+ */
+ WRITE_ONCE(scx_switching_all, !(ops->flags & SCX_OPS_SWITCH_PARTIAL));
+ static_branch_enable(&__scx_ops_enabled);
+
+ /*
+ * We're fully committed and can't fail. The task READY -> ENABLED
+ * transitions here are synchronized against sched_ext_free() through
+ * scx_tasks_lock.
+ */
+ percpu_down_write(&scx_fork_rwsem);
+ scx_task_iter_start(&sti);
+ while ((p = scx_task_iter_next_locked(&sti))) {
+ const struct sched_class *old_class = p->sched_class;
+ struct sched_enq_and_set_ctx ctx;
+
+ sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
+
+ p->scx.slice = SCX_SLICE_DFL;
+ __setscheduler_prio(p, p->prio);
+ check_class_changing(task_rq(p), p, old_class);
+
+ sched_enq_and_set_task(&ctx);
+
+ check_class_changed(task_rq(p), p, old_class, p->prio);
+ }
+ scx_task_iter_stop(&sti);
+ percpu_up_write(&scx_fork_rwsem);
+
+ scx_ops_bypass(false);
+
+ /*
+ * Returning an error code here would lose the recorded error
+ * information. Exit indicating success so that the error is notified
+ * through ops.exit() with all the details.
+ */
+ if (!scx_ops_tryset_enable_state(SCX_OPS_ENABLED, SCX_OPS_ENABLING)) {
+ WARN_ON_ONCE(atomic_read(&scx_exit_kind) == SCX_EXIT_NONE);
+ ret = 0;
+ goto err_disable;
+ }
+
+ if (!(ops->flags & SCX_OPS_SWITCH_PARTIAL))
+ static_branch_enable(&__scx_switched_all);
+
+ pr_info("sched_ext: BPF scheduler \"%s\" enabled%s\n",
+ scx_ops.name, scx_switched_all() ? "" : " (partial)");
+ kobject_uevent(scx_root_kobj, KOBJ_ADD);
+ mutex_unlock(&scx_ops_enable_mutex);
+
+ atomic_long_inc(&scx_enable_seq);
+
+ return 0;
+
+err_del:
+ kobject_del(scx_root_kobj);
+err:
+ kobject_put(scx_root_kobj);
+ scx_root_kobj = NULL;
+ if (scx_exit_info) {
+ free_exit_info(scx_exit_info);
+ scx_exit_info = NULL;
+ }
+err_unlock:
+ mutex_unlock(&scx_ops_enable_mutex);
+ return ret;
+
+err_disable_unlock_all:
+ scx_cgroup_unlock();
+ percpu_up_write(&scx_fork_rwsem);
+ scx_ops_bypass(false);
+err_disable:
+ mutex_unlock(&scx_ops_enable_mutex);
+ /* must be fully disabled before returning */
+ scx_ops_disable(SCX_EXIT_ERROR);
+ kthread_flush_work(&scx_ops_disable_work);
+ return ret;
+}
+
+
+/********************************************************************************
+ * bpf_struct_ops plumbing.
+ */
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+
+extern struct btf *btf_vmlinux;
+static const struct btf_type *task_struct_type;
+static u32 task_struct_type_id;
+
+static bool set_arg_maybe_null(const char *op, int arg_n, int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ struct btf *btf = bpf_get_btf_vmlinux();
+ const struct bpf_struct_ops_desc *st_ops_desc;
+ const struct btf_member *member;
+ const struct btf_type *t;
+ u32 btf_id, member_idx;
+ const char *mname;
+
+ /* struct_ops op args are all sequential, 64-bit numbers */
+ if (off != arg_n * sizeof(__u64))
+ return false;
+
+ /* btf_id should be the type id of struct sched_ext_ops */
+ btf_id = prog->aux->attach_btf_id;
+ st_ops_desc = bpf_struct_ops_find(btf, btf_id);
+ if (!st_ops_desc)
+ return false;
+
+ /* BTF type of struct sched_ext_ops */
+ t = st_ops_desc->type;
+
+ member_idx = prog->expected_attach_type;
+ if (member_idx >= btf_type_vlen(t))
+ return false;
+
+ /*
+ * Get the member name of this struct_ops program, which corresponds to
+ * a field in struct sched_ext_ops. For example, the member name of the
+ * dispatch struct_ops program (callback) is "dispatch".
+ */
+ member = &btf_type_member(t)[member_idx];
+ mname = btf_name_by_offset(btf_vmlinux, member->name_off);
+
+ if (!strcmp(mname, op)) {
+ /*
+ * The value is a pointer to a type (struct task_struct) given
+ * by a BTF ID (PTR_TO_BTF_ID). It is trusted (PTR_TRUSTED),
+ * however, can be a NULL (PTR_MAYBE_NULL). The BPF program
+ * should check the pointer to make sure it is not NULL before
+ * using it, or the verifier will reject the program.
+ *
+ * Longer term, this is something that should be addressed by
+ * BTF, and be fully contained within the verifier.
+ */
+ info->reg_type = PTR_MAYBE_NULL | PTR_TO_BTF_ID | PTR_TRUSTED;
+ info->btf = btf_vmlinux;
+ info->btf_id = task_struct_type_id;
+
+ return true;
+ }
+
+ return false;
+}
+
+static bool bpf_scx_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ if (type != BPF_READ)
+ return false;
+ if (set_arg_maybe_null("dispatch", 1, off, size, type, prog, info) ||
+ set_arg_maybe_null("yield", 1, off, size, type, prog, info))
+ return true;
+ if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS)
+ return false;
+ if (off % size != 0)
+ return false;
+
+ return btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
+ const struct bpf_reg_state *reg, int off,
+ int size)
+{
+ const struct btf_type *t;
+
+ t = btf_type_by_id(reg->btf, reg->btf_id);
+ if (t == task_struct_type) {
+ if (off >= offsetof(struct task_struct, scx.slice) &&
+ off + size <= offsetofend(struct task_struct, scx.slice))
+ return SCALAR_VALUE;
+ if (off >= offsetof(struct task_struct, scx.dsq_vtime) &&
+ off + size <= offsetofend(struct task_struct, scx.dsq_vtime))
+ return SCALAR_VALUE;
+ if (off >= offsetof(struct task_struct, scx.disallow) &&
+ off + size <= offsetofend(struct task_struct, scx.disallow))
+ return SCALAR_VALUE;
+ }
+
+ return -EACCES;
+}
+
+static const struct bpf_func_proto *
+bpf_scx_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_task_storage_get:
+ return &bpf_task_storage_get_proto;
+ case BPF_FUNC_task_storage_delete:
+ return &bpf_task_storage_delete_proto;
+ default:
+ return bpf_base_func_proto(func_id, prog);
+ }
+}
+
+static const struct bpf_verifier_ops bpf_scx_verifier_ops = {
+ .get_func_proto = bpf_scx_get_func_proto,
+ .is_valid_access = bpf_scx_is_valid_access,
+ .btf_struct_access = bpf_scx_btf_struct_access,
+};
+
+static int bpf_scx_init_member(const struct btf_type *t,
+ const struct btf_member *member,
+ void *kdata, const void *udata)
+{
+ const struct sched_ext_ops *uops = udata;
+ struct sched_ext_ops *ops = kdata;
+ u32 moff = __btf_member_bit_offset(t, member) / 8;
+ int ret;
+
+ switch (moff) {
+ case offsetof(struct sched_ext_ops, dispatch_max_batch):
+ if (*(u32 *)(udata + moff) > INT_MAX)
+ return -E2BIG;
+ ops->dispatch_max_batch = *(u32 *)(udata + moff);
+ return 1;
+ case offsetof(struct sched_ext_ops, flags):
+ if (*(u64 *)(udata + moff) & ~SCX_OPS_ALL_FLAGS)
+ return -EINVAL;
+ ops->flags = *(u64 *)(udata + moff);
+ return 1;
+ case offsetof(struct sched_ext_ops, name):
+ ret = bpf_obj_name_cpy(ops->name, uops->name,
+ sizeof(ops->name));
+ if (ret < 0)
+ return ret;
+ if (ret == 0)
+ return -EINVAL;
+ return 1;
+ case offsetof(struct sched_ext_ops, timeout_ms):
+ if (msecs_to_jiffies(*(u32 *)(udata + moff)) >
+ SCX_WATCHDOG_MAX_TIMEOUT)
+ return -E2BIG;
+ ops->timeout_ms = *(u32 *)(udata + moff);
+ return 1;
+ case offsetof(struct sched_ext_ops, exit_dump_len):
+ ops->exit_dump_len =
+ *(u32 *)(udata + moff) ?: SCX_EXIT_DUMP_DFL_LEN;
+ return 1;
+ case offsetof(struct sched_ext_ops, hotplug_seq):
+ ops->hotplug_seq = *(u64 *)(udata + moff);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int bpf_scx_check_member(const struct btf_type *t,
+ const struct btf_member *member,
+ const struct bpf_prog *prog)
+{
+ u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+ switch (moff) {
+ case offsetof(struct sched_ext_ops, init_task):
+#ifdef CONFIG_EXT_GROUP_SCHED
+ case offsetof(struct sched_ext_ops, cgroup_init):
+ case offsetof(struct sched_ext_ops, cgroup_exit):
+ case offsetof(struct sched_ext_ops, cgroup_prep_move):
+#endif
+ case offsetof(struct sched_ext_ops, cpu_online):
+ case offsetof(struct sched_ext_ops, cpu_offline):
+ case offsetof(struct sched_ext_ops, init):
+ case offsetof(struct sched_ext_ops, exit):
+ break;
+ default:
+ if (prog->sleepable)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int bpf_scx_reg(void *kdata, struct bpf_link *link)
+{
+ return scx_ops_enable(kdata, link);
+}
+
+static void bpf_scx_unreg(void *kdata, struct bpf_link *link)
+{
+ scx_ops_disable(SCX_EXIT_UNREG);
+ kthread_flush_work(&scx_ops_disable_work);
+}
+
+static int bpf_scx_init(struct btf *btf)
+{
+ s32 type_id;
+
+ type_id = btf_find_by_name_kind(btf, "task_struct", BTF_KIND_STRUCT);
+ if (type_id < 0)
+ return -EINVAL;
+ task_struct_type = btf_type_by_id(btf, type_id);
+ task_struct_type_id = type_id;
+
+ return 0;
+}
+
+static int bpf_scx_update(void *kdata, void *old_kdata, struct bpf_link *link)
+{
+ /*
+ * sched_ext does not support updating the actively-loaded BPF
+ * scheduler, as registering a BPF scheduler can always fail if the
+ * scheduler returns an error code for e.g. ops.init(), ops.init_task(),
+ * etc. Similarly, we can always race with unregistration happening
+ * elsewhere, such as with sysrq.
+ */
+ return -EOPNOTSUPP;
+}
+
+static int bpf_scx_validate(void *kdata)
+{
+ return 0;
+}
+
+static s32 select_cpu_stub(struct task_struct *p, s32 prev_cpu, u64 wake_flags) { return -EINVAL; }
+static void enqueue_stub(struct task_struct *p, u64 enq_flags) {}
+static void dequeue_stub(struct task_struct *p, u64 enq_flags) {}
+static void dispatch_stub(s32 prev_cpu, struct task_struct *p) {}
+static void tick_stub(struct task_struct *p) {}
+static void runnable_stub(struct task_struct *p, u64 enq_flags) {}
+static void running_stub(struct task_struct *p) {}
+static void stopping_stub(struct task_struct *p, bool runnable) {}
+static void quiescent_stub(struct task_struct *p, u64 deq_flags) {}
+static bool yield_stub(struct task_struct *from, struct task_struct *to) { return false; }
+static bool core_sched_before_stub(struct task_struct *a, struct task_struct *b) { return false; }
+static void set_weight_stub(struct task_struct *p, u32 weight) {}
+static void set_cpumask_stub(struct task_struct *p, const struct cpumask *mask) {}
+static void update_idle_stub(s32 cpu, bool idle) {}
+static void cpu_acquire_stub(s32 cpu, struct scx_cpu_acquire_args *args) {}
+static void cpu_release_stub(s32 cpu, struct scx_cpu_release_args *args) {}
+static s32 init_task_stub(struct task_struct *p, struct scx_init_task_args *args) { return -EINVAL; }
+static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {}
+static void enable_stub(struct task_struct *p) {}
+static void disable_stub(struct task_struct *p) {}
+#ifdef CONFIG_EXT_GROUP_SCHED
+static s32 cgroup_init_stub(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; }
+static void cgroup_exit_stub(struct cgroup *cgrp) {}
+static s32 cgroup_prep_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; }
+static void cgroup_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void cgroup_cancel_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void cgroup_set_weight_stub(struct cgroup *cgrp, u32 weight) {}
+#endif
+static void cpu_online_stub(s32 cpu) {}
+static void cpu_offline_stub(s32 cpu) {}
+static s32 init_stub(void) { return -EINVAL; }
+static void exit_stub(struct scx_exit_info *info) {}
+static void dump_stub(struct scx_dump_ctx *ctx) {}
+static void dump_cpu_stub(struct scx_dump_ctx *ctx, s32 cpu, bool idle) {}
+static void dump_task_stub(struct scx_dump_ctx *ctx, struct task_struct *p) {}
+
+static struct sched_ext_ops __bpf_ops_sched_ext_ops = {
+ .select_cpu = select_cpu_stub,
+ .enqueue = enqueue_stub,
+ .dequeue = dequeue_stub,
+ .dispatch = dispatch_stub,
+ .tick = tick_stub,
+ .runnable = runnable_stub,
+ .running = running_stub,
+ .stopping = stopping_stub,
+ .quiescent = quiescent_stub,
+ .yield = yield_stub,
+ .core_sched_before = core_sched_before_stub,
+ .set_weight = set_weight_stub,
+ .set_cpumask = set_cpumask_stub,
+ .update_idle = update_idle_stub,
+ .cpu_acquire = cpu_acquire_stub,
+ .cpu_release = cpu_release_stub,
+ .init_task = init_task_stub,
+ .exit_task = exit_task_stub,
+ .enable = enable_stub,
+ .disable = disable_stub,
+#ifdef CONFIG_EXT_GROUP_SCHED
+ .cgroup_init = cgroup_init_stub,
+ .cgroup_exit = cgroup_exit_stub,
+ .cgroup_prep_move = cgroup_prep_move_stub,
+ .cgroup_move = cgroup_move_stub,
+ .cgroup_cancel_move = cgroup_cancel_move_stub,
+ .cgroup_set_weight = cgroup_set_weight_stub,
+#endif
+ .cpu_online = cpu_online_stub,
+ .cpu_offline = cpu_offline_stub,
+ .init = init_stub,
+ .exit = exit_stub,
+ .dump = dump_stub,
+ .dump_cpu = dump_cpu_stub,
+ .dump_task = dump_task_stub,
+};
+
+static struct bpf_struct_ops bpf_sched_ext_ops = {
+ .verifier_ops = &bpf_scx_verifier_ops,
+ .reg = bpf_scx_reg,
+ .unreg = bpf_scx_unreg,
+ .check_member = bpf_scx_check_member,
+ .init_member = bpf_scx_init_member,
+ .init = bpf_scx_init,
+ .update = bpf_scx_update,
+ .validate = bpf_scx_validate,
+ .name = "sched_ext_ops",
+ .owner = THIS_MODULE,
+ .cfi_stubs = &__bpf_ops_sched_ext_ops
+};
+
+
+/********************************************************************************
+ * System integration and init.
+ */
+
+static void sysrq_handle_sched_ext_reset(u8 key)
+{
+ if (scx_ops_helper)
+ scx_ops_disable(SCX_EXIT_SYSRQ);
+ else
+ pr_info("sched_ext: BPF scheduler not yet used\n");
+}
+
+static const struct sysrq_key_op sysrq_sched_ext_reset_op = {
+ .handler = sysrq_handle_sched_ext_reset,
+ .help_msg = "reset-sched-ext(S)",
+ .action_msg = "Disable sched_ext and revert all tasks to CFS",
+ .enable_mask = SYSRQ_ENABLE_RTNICE,
+};
+
+static void sysrq_handle_sched_ext_dump(u8 key)
+{
+ struct scx_exit_info ei = { .kind = SCX_EXIT_NONE, .reason = "SysRq-D" };
+
+ if (scx_enabled())
+ scx_dump_state(&ei, 0);
+}
+
+static const struct sysrq_key_op sysrq_sched_ext_dump_op = {
+ .handler = sysrq_handle_sched_ext_dump,
+ .help_msg = "dump-sched-ext(D)",
+ .action_msg = "Trigger sched_ext debug dump",
+ .enable_mask = SYSRQ_ENABLE_RTNICE,
+};
+
+static bool can_skip_idle_kick(struct rq *rq)
+{
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * We can skip idle kicking if @rq is going to go through at least one
+ * full SCX scheduling cycle before going idle. Just checking whether
+ * curr is not idle is insufficient because we could be racing
+ * balance_one() trying to pull the next task from a remote rq, which
+ * may fail, and @rq may become idle afterwards.
+ *
+ * The race window is small and we don't and can't guarantee that @rq is
+ * only kicked while idle anyway. Skip only when sure.
+ */
+ return !is_idle_task(rq->curr) && !(rq->scx.flags & SCX_RQ_IN_BALANCE);
+}
+
+static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs)
+{
+ struct rq *rq = cpu_rq(cpu);
+ struct scx_rq *this_scx = &this_rq->scx;
+ bool should_wait = false;
+ unsigned long flags;
+
+ raw_spin_rq_lock_irqsave(rq, flags);
+
+ /*
+ * During CPU hotplug, a CPU may depend on kicking itself to make
+ * forward progress. Allow kicking self regardless of online state.
+ */
+ if (cpu_online(cpu) || cpu == cpu_of(this_rq)) {
+ if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) {
+ if (rq->curr->sched_class == &ext_sched_class)
+ rq->curr->scx.slice = 0;
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt);
+ }
+
+ if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) {
+ pseqs[cpu] = rq->scx.pnt_seq;
+ should_wait = true;
+ }
+
+ resched_curr(rq);
+ } else {
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt);
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
+ }
+
+ raw_spin_rq_unlock_irqrestore(rq, flags);
+
+ return should_wait;
+}
+
+static void kick_one_cpu_if_idle(s32 cpu, struct rq *this_rq)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ raw_spin_rq_lock_irqsave(rq, flags);
+
+ if (!can_skip_idle_kick(rq) &&
+ (cpu_online(cpu) || cpu == cpu_of(this_rq)))
+ resched_curr(rq);
+
+ raw_spin_rq_unlock_irqrestore(rq, flags);
+}
+
+static void kick_cpus_irq_workfn(struct irq_work *irq_work)
+{
+ struct rq *this_rq = this_rq();
+ struct scx_rq *this_scx = &this_rq->scx;
+ unsigned long *pseqs = this_cpu_ptr(scx_kick_cpus_pnt_seqs);
+ bool should_wait = false;
+ s32 cpu;
+
+ for_each_cpu(cpu, this_scx->cpus_to_kick) {
+ should_wait |= kick_one_cpu(cpu, this_rq, pseqs);
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_kick);
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
+ }
+
+ for_each_cpu(cpu, this_scx->cpus_to_kick_if_idle) {
+ kick_one_cpu_if_idle(cpu, this_rq);
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_kick_if_idle);
+ }
+
+ if (!should_wait)
+ return;
+
+ for_each_cpu(cpu, this_scx->cpus_to_wait) {
+ unsigned long *wait_pnt_seq = &cpu_rq(cpu)->scx.pnt_seq;
+
+ if (cpu != cpu_of(this_rq)) {
+ /*
+ * Pairs with smp_store_release() issued by this CPU in
+ * scx_next_task_picked() on the resched path.
+ *
+ * We busy-wait here to guarantee that no other task can
+ * be scheduled on our core before the target CPU has
+ * entered the resched path.
+ */
+ while (smp_load_acquire(wait_pnt_seq) == pseqs[cpu])
+ cpu_relax();
+ }
+
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
+ }
+}
+
+/**
+ * print_scx_info - print out sched_ext scheduler state
+ * @log_lvl: the log level to use when printing
+ * @p: target task
+ *
+ * If a sched_ext scheduler is enabled, print the name and state of the
+ * scheduler. If @p is on sched_ext, print further information about the task.
+ *
+ * This function can be safely called on any task as long as the task_struct
+ * itself is accessible. While safe, this function isn't synchronized and may
+ * print out mixups or garbages of limited length.
+ */
+void print_scx_info(const char *log_lvl, struct task_struct *p)
+{
+ enum scx_ops_enable_state state = scx_ops_enable_state();
+ const char *all = READ_ONCE(scx_switching_all) ? "+all" : "";
+ char runnable_at_buf[22] = "?";
+ struct sched_class *class;
+ unsigned long runnable_at;
+
+ if (state == SCX_OPS_DISABLED)
+ return;
+
+ /*
+ * Carefully check if the task was running on sched_ext, and then
+ * carefully copy the time it's been runnable, and its state.
+ */
+ if (copy_from_kernel_nofault(&class, &p->sched_class, sizeof(class)) ||
+ class != &ext_sched_class) {
+ printk("%sSched_ext: %s (%s%s)", log_lvl, scx_ops.name,
+ scx_ops_enable_state_str[state], all);
+ return;
+ }
+
+ if (!copy_from_kernel_nofault(&runnable_at, &p->scx.runnable_at,
+ sizeof(runnable_at)))
+ scnprintf(runnable_at_buf, sizeof(runnable_at_buf), "%+ldms",
+ jiffies_delta_msecs(runnable_at, jiffies));
+
+ /* print everything onto one line to conserve console space */
+ printk("%sSched_ext: %s (%s%s), task: runnable_at=%s",
+ log_lvl, scx_ops.name, scx_ops_enable_state_str[state], all,
+ runnable_at_buf);
+}
+
+static int scx_pm_handler(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+ /*
+ * SCX schedulers often have userspace components which are sometimes
+ * involved in critial scheduling paths. PM operations involve freezing
+ * userspace which can lead to scheduling misbehaviors including stalls.
+ * Let's bypass while PM operations are in progress.
+ */
+ switch (event) {
+ case PM_HIBERNATION_PREPARE:
+ case PM_SUSPEND_PREPARE:
+ case PM_RESTORE_PREPARE:
+ scx_ops_bypass(true);
+ break;
+ case PM_POST_HIBERNATION:
+ case PM_POST_SUSPEND:
+ case PM_POST_RESTORE:
+ scx_ops_bypass(false);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block scx_pm_notifier = {
+ .notifier_call = scx_pm_handler,
+};
+
+void __init init_sched_ext_class(void)
+{
+ s32 cpu, v;
+
+ /*
+ * The following is to prevent the compiler from optimizing out the enum
+ * definitions so that BPF scheduler implementations can use them
+ * through the generated vmlinux.h.
+ */
+ WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT |
+ SCX_TG_ONLINE);
+
+ BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params));
+#ifdef CONFIG_SMP
+ BUG_ON(!alloc_cpumask_var(&idle_masks.cpu, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&idle_masks.smt, GFP_KERNEL));
+#endif
+ scx_kick_cpus_pnt_seqs =
+ __alloc_percpu(sizeof(scx_kick_cpus_pnt_seqs[0]) * nr_cpu_ids,
+ __alignof__(scx_kick_cpus_pnt_seqs[0]));
+ BUG_ON(!scx_kick_cpus_pnt_seqs);
+
+ for_each_possible_cpu(cpu) {
+ struct rq *rq = cpu_rq(cpu);
+
+ init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL);
+ INIT_LIST_HEAD(&rq->scx.runnable_list);
+ INIT_LIST_HEAD(&rq->scx.ddsp_deferred_locals);
+
+ BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_preempt, GFP_KERNEL));
+ BUG_ON(!zalloc_cpumask_var(&rq->scx.cpus_to_wait, GFP_KERNEL));
+ init_irq_work(&rq->scx.deferred_irq_work, deferred_irq_workfn);
+ init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn);
+
+ if (cpu_online(cpu))
+ cpu_rq(cpu)->scx.flags |= SCX_RQ_ONLINE;
+ }
+
+ register_sysrq_key('S', &sysrq_sched_ext_reset_op);
+ register_sysrq_key('D', &sysrq_sched_ext_dump_op);
+ INIT_DELAYED_WORK(&scx_watchdog_work, scx_watchdog_workfn);
+}
+
+
+/********************************************************************************
+ * Helpers that can be called from the BPF scheduler.
+ */
+#include <linux/btf_ids.h>
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu()
+ * @p: task_struct to select a CPU for
+ * @prev_cpu: CPU @p was on previously
+ * @wake_flags: %SCX_WAKE_* flags
+ * @is_idle: out parameter indicating whether the returned CPU is idle
+ *
+ * Can only be called from ops.select_cpu() if the built-in CPU selection is
+ * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set.
+ * @p, @prev_cpu and @wake_flags match ops.select_cpu().
+ *
+ * Returns the picked CPU with *@is_idle indicating whether the picked CPU is
+ * currently idle and thus a good candidate for direct dispatching.
+ */
+__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
+ u64 wake_flags, bool *is_idle)
+{
+ if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+ scx_ops_error("built-in idle tracking is disabled");
+ goto prev_cpu;
+ }
+
+ if (!scx_kf_allowed(SCX_KF_SELECT_CPU))
+ goto prev_cpu;
+
+#ifdef CONFIG_SMP
+ return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle);
+#endif
+
+prev_cpu:
+ *is_idle = false;
+ return prev_cpu;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_select_cpu)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_select_cpu)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_select_cpu,
+};
+
+static bool scx_dispatch_preamble(struct task_struct *p, u64 enq_flags)
+{
+ if (!scx_kf_allowed(SCX_KF_ENQUEUE | SCX_KF_DISPATCH))
+ return false;
+
+ lockdep_assert_irqs_disabled();
+
+ if (unlikely(!p)) {
+ scx_ops_error("called with NULL task");
+ return false;
+ }
+
+ if (unlikely(enq_flags & __SCX_ENQ_INTERNAL_MASK)) {
+ scx_ops_error("invalid enq_flags 0x%llx", enq_flags);
+ return false;
+ }
+
+ return true;
+}
+
+static void scx_dispatch_commit(struct task_struct *p, u64 dsq_id, u64 enq_flags)
+{
+ struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
+ struct task_struct *ddsp_task;
+
+ ddsp_task = __this_cpu_read(direct_dispatch_task);
+ if (ddsp_task) {
+ mark_direct_dispatch(ddsp_task, p, dsq_id, enq_flags);
+ return;
+ }
+
+ if (unlikely(dspc->cursor >= scx_dsp_max_batch)) {
+ scx_ops_error("dispatch buffer overflow");
+ return;
+ }
+
+ dspc->buf[dspc->cursor++] = (struct scx_dsp_buf_ent){
+ .task = p,
+ .qseq = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_QSEQ_MASK,
+ .dsq_id = dsq_id,
+ .enq_flags = enq_flags,
+ };
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_dispatch - Dispatch a task into the FIFO queue of a DSQ
+ * @p: task_struct to dispatch
+ * @dsq_id: DSQ to dispatch to
+ * @slice: duration @p can run for in nsecs, 0 to keep the current value
+ * @enq_flags: SCX_ENQ_*
+ *
+ * Dispatch @p into the FIFO queue of the DSQ identified by @dsq_id. It is safe
+ * to call this function spuriously. Can be called from ops.enqueue(),
+ * ops.select_cpu(), and ops.dispatch().
+ *
+ * When called from ops.select_cpu() or ops.enqueue(), it's for direct dispatch
+ * and @p must match the task being enqueued. Also, %SCX_DSQ_LOCAL_ON can't be
+ * used to target the local DSQ of a CPU other than the enqueueing one. Use
+ * ops.select_cpu() to be on the target CPU in the first place.
+ *
+ * When called from ops.select_cpu(), @enq_flags and @dsp_id are stored, and @p
+ * will be directly dispatched to the corresponding dispatch queue after
+ * ops.select_cpu() returns. If @p is dispatched to SCX_DSQ_LOCAL, it will be
+ * dispatched to the local DSQ of the CPU returned by ops.select_cpu().
+ * @enq_flags are OR'd with the enqueue flags on the enqueue path before the
+ * task is dispatched.
+ *
+ * When called from ops.dispatch(), there are no restrictions on @p or @dsq_id
+ * and this function can be called upto ops.dispatch_max_batch times to dispatch
+ * multiple tasks. scx_bpf_dispatch_nr_slots() returns the number of the
+ * remaining slots. scx_bpf_consume() flushes the batch and resets the counter.
+ *
+ * This function doesn't have any locking restrictions and may be called under
+ * BPF locks (in the future when BPF introduces more flexible locking).
+ *
+ * @p is allowed to run for @slice. The scheduling path is triggered on slice
+ * exhaustion. If zero, the current residual slice is maintained. If
+ * %SCX_SLICE_INF, @p never expires and the BPF scheduler must kick the CPU with
+ * scx_bpf_kick_cpu() to trigger scheduling.
+ */
+__bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice,
+ u64 enq_flags)
+{
+ if (!scx_dispatch_preamble(p, enq_flags))
+ return;
+
+ if (slice)
+ p->scx.slice = slice;
+ else
+ p->scx.slice = p->scx.slice ?: 1;
+
+ scx_dispatch_commit(p, dsq_id, enq_flags);
+}
+
+/**
+ * scx_bpf_dispatch_vtime - Dispatch a task into the vtime priority queue of a DSQ
+ * @p: task_struct to dispatch
+ * @dsq_id: DSQ to dispatch to
+ * @slice: duration @p can run for in nsecs, 0 to keep the current value
+ * @vtime: @p's ordering inside the vtime-sorted queue of the target DSQ
+ * @enq_flags: SCX_ENQ_*
+ *
+ * Dispatch @p into the vtime priority queue of the DSQ identified by @dsq_id.
+ * Tasks queued into the priority queue are ordered by @vtime and always
+ * consumed after the tasks in the FIFO queue. All other aspects are identical
+ * to scx_bpf_dispatch().
+ *
+ * @vtime ordering is according to time_before64() which considers wrapping. A
+ * numerically larger vtime may indicate an earlier position in the ordering and
+ * vice-versa.
+ */
+__bpf_kfunc void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id,
+ u64 slice, u64 vtime, u64 enq_flags)
+{
+ if (!scx_dispatch_preamble(p, enq_flags))
+ return;
+
+ if (slice)
+ p->scx.slice = slice;
+ else
+ p->scx.slice = p->scx.slice ?: 1;
+
+ p->scx.dsq_vtime = vtime;
+
+ scx_dispatch_commit(p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch)
+BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime, KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_enqueue_dispatch,
+};
+
+static bool scx_dispatch_from_dsq(struct bpf_iter_scx_dsq_kern *kit,
+ struct task_struct *p, u64 dsq_id,
+ u64 enq_flags)
+{
+ struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq;
+ struct rq *this_rq, *src_rq, *dst_rq, *locked_rq;
+ bool dispatched = false;
+ bool in_balance;
+ unsigned long flags;
+
+ if (!scx_kf_allowed_if_unlocked() && !scx_kf_allowed(SCX_KF_DISPATCH))
+ return false;
+
+ /*
+ * Can be called from either ops.dispatch() locking this_rq() or any
+ * context where no rq lock is held. If latter, lock @p's task_rq which
+ * we'll likely need anyway.
+ */
+ src_rq = task_rq(p);
+
+ local_irq_save(flags);
+ this_rq = this_rq();
+ in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE;
+
+ if (in_balance) {
+ if (this_rq != src_rq) {
+ raw_spin_rq_unlock(this_rq);
+ raw_spin_rq_lock(src_rq);
+ }
+ } else {
+ raw_spin_rq_lock(src_rq);
+ }
+
+ locked_rq = src_rq;
+ raw_spin_lock(&src_dsq->lock);
+
+ /*
+ * Did someone else get to it? @p could have already left $src_dsq, got
+ * re-enqueud, or be in the process of being consumed by someone else.
+ */
+ if (unlikely(p->scx.dsq != src_dsq ||
+ u32_before(kit->cursor.priv, p->scx.dsq_seq) ||
+ p->scx.holding_cpu >= 0) ||
+ WARN_ON_ONCE(src_rq != task_rq(p))) {
+ raw_spin_unlock(&src_dsq->lock);
+ goto out;
+ }
+
+ /* @p is still on $src_dsq and stable, determine the destination */
+ dst_dsq = find_dsq_for_dispatch(this_rq, dsq_id, p);
+
+ if (dst_dsq->id == SCX_DSQ_LOCAL) {
+ dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
+ if (!task_can_run_on_remote_rq(p, dst_rq, true)) {
+ dst_dsq = find_global_dsq(p);
+ dst_rq = src_rq;
+ }
+ } else {
+ /* no need to migrate if destination is a non-local DSQ */
+ dst_rq = src_rq;
+ }
+
+ /*
+ * Move @p into $dst_dsq. If $dst_dsq is the local DSQ of a different
+ * CPU, @p will be migrated.
+ */
+ if (dst_dsq->id == SCX_DSQ_LOCAL) {
+ /* @p is going from a non-local DSQ to a local DSQ */
+ if (src_rq == dst_rq) {
+ task_unlink_from_dsq(p, src_dsq);
+ move_local_task_to_local_dsq(p, enq_flags,
+ src_dsq, dst_rq);
+ raw_spin_unlock(&src_dsq->lock);
+ } else {
+ raw_spin_unlock(&src_dsq->lock);
+ move_remote_task_to_local_dsq(p, enq_flags,
+ src_rq, dst_rq);
+ locked_rq = dst_rq;
+ }
+ } else {
+ /*
+ * @p is going from a non-local DSQ to a non-local DSQ. As
+ * $src_dsq is already locked, do an abbreviated dequeue.
+ */
+ task_unlink_from_dsq(p, src_dsq);
+ p->scx.dsq = NULL;
+ raw_spin_unlock(&src_dsq->lock);
+
+ if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_VTIME)
+ p->scx.dsq_vtime = kit->vtime;
+ dispatch_enqueue(dst_dsq, p, enq_flags);
+ }
+
+ if (kit->cursor.flags & __SCX_DSQ_ITER_HAS_SLICE)
+ p->scx.slice = kit->slice;
+
+ dispatched = true;
+out:
+ if (in_balance) {
+ if (this_rq != locked_rq) {
+ raw_spin_rq_unlock(locked_rq);
+ raw_spin_rq_lock(this_rq);
+ }
+ } else {
+ raw_spin_rq_unlock_irqrestore(locked_rq, flags);
+ }
+
+ kit->cursor.flags &= ~(__SCX_DSQ_ITER_HAS_SLICE |
+ __SCX_DSQ_ITER_HAS_VTIME);
+ return dispatched;
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_dispatch_nr_slots - Return the number of remaining dispatch slots
+ *
+ * Can only be called from ops.dispatch().
+ */
+__bpf_kfunc u32 scx_bpf_dispatch_nr_slots(void)
+{
+ if (!scx_kf_allowed(SCX_KF_DISPATCH))
+ return 0;
+
+ return scx_dsp_max_batch - __this_cpu_read(scx_dsp_ctx->cursor);
+}
+
+/**
+ * scx_bpf_dispatch_cancel - Cancel the latest dispatch
+ *
+ * Cancel the latest dispatch. Can be called multiple times to cancel further
+ * dispatches. Can only be called from ops.dispatch().
+ */
+__bpf_kfunc void scx_bpf_dispatch_cancel(void)
+{
+ struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
+
+ if (!scx_kf_allowed(SCX_KF_DISPATCH))
+ return;
+
+ if (dspc->cursor > 0)
+ dspc->cursor--;
+ else
+ scx_ops_error("dispatch buffer underflow");
+}
+
+/**
+ * scx_bpf_consume - Transfer a task from a DSQ to the current CPU's local DSQ
+ * @dsq_id: DSQ to consume
+ *
+ * Consume a task from the non-local DSQ identified by @dsq_id and transfer it
+ * to the current CPU's local DSQ for execution. Can only be called from
+ * ops.dispatch().
+ *
+ * This function flushes the in-flight dispatches from scx_bpf_dispatch() before
+ * trying to consume the specified DSQ. It may also grab rq locks and thus can't
+ * be called under any BPF locks.
+ *
+ * Returns %true if a task has been consumed, %false if there isn't any task to
+ * consume.
+ */
+__bpf_kfunc bool scx_bpf_consume(u64 dsq_id)
+{
+ struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx);
+ struct scx_dispatch_q *dsq;
+
+ if (!scx_kf_allowed(SCX_KF_DISPATCH))
+ return false;
+
+ flush_dispatch_buf(dspc->rq);
+
+ dsq = find_user_dsq(dsq_id);
+ if (unlikely(!dsq)) {
+ scx_ops_error("invalid DSQ ID 0x%016llx", dsq_id);
+ return false;
+ }
+
+ if (consume_dispatch_q(dspc->rq, dsq)) {
+ /*
+ * A successfully consumed task can be dequeued before it starts
+ * running while the CPU is trying to migrate other dispatched
+ * tasks. Bump nr_tasks to tell balance_scx() to retry on empty
+ * local DSQ.
+ */
+ dspc->nr_tasks++;
+ return true;
+ } else {
+ return false;
+ }
+}
+
+/**
+ * scx_bpf_dispatch_from_dsq_set_slice - Override slice when dispatching from DSQ
+ * @it__iter: DSQ iterator in progress
+ * @slice: duration the dispatched task can run for in nsecs
+ *
+ * Override the slice of the next task that will be dispatched from @it__iter
+ * using scx_bpf_dispatch_from_dsq[_vtime](). If this function is not called,
+ * the previous slice duration is kept.
+ */
+__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_slice(
+ struct bpf_iter_scx_dsq *it__iter, u64 slice)
+{
+ struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter;
+
+ kit->slice = slice;
+ kit->cursor.flags |= __SCX_DSQ_ITER_HAS_SLICE;
+}
+
+/**
+ * scx_bpf_dispatch_from_dsq_set_vtime - Override vtime when dispatching from DSQ
+ * @it__iter: DSQ iterator in progress
+ * @vtime: task's ordering inside the vtime-sorted queue of the target DSQ
+ *
+ * Override the vtime of the next task that will be dispatched from @it__iter
+ * using scx_bpf_dispatch_from_dsq_vtime(). If this function is not called, the
+ * previous slice vtime is kept. If scx_bpf_dispatch_from_dsq() is used to
+ * dispatch the next task, the override is ignored and cleared.
+ */
+__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_vtime(
+ struct bpf_iter_scx_dsq *it__iter, u64 vtime)
+{
+ struct bpf_iter_scx_dsq_kern *kit = (void *)it__iter;
+
+ kit->vtime = vtime;
+ kit->cursor.flags |= __SCX_DSQ_ITER_HAS_VTIME;
+}
+
+/**
+ * scx_bpf_dispatch_from_dsq - Move a task from DSQ iteration to a DSQ
+ * @it__iter: DSQ iterator in progress
+ * @p: task to transfer
+ * @dsq_id: DSQ to move @p to
+ * @enq_flags: SCX_ENQ_*
+ *
+ * Transfer @p which is on the DSQ currently iterated by @it__iter to the DSQ
+ * specified by @dsq_id. All DSQs - local DSQs, global DSQ and user DSQs - can
+ * be the destination.
+ *
+ * For the transfer to be successful, @p must still be on the DSQ and have been
+ * queued before the DSQ iteration started. This function doesn't care whether
+ * @p was obtained from the DSQ iteration. @p just has to be on the DSQ and have
+ * been queued before the iteration started.
+ *
+ * @p's slice is kept by default. Use scx_bpf_dispatch_from_dsq_set_slice() to
+ * update.
+ *
+ * Can be called from ops.dispatch() or any BPF context which doesn't hold a rq
+ * lock (e.g. BPF timers or SYSCALL programs).
+ *
+ * Returns %true if @p has been consumed, %false if @p had already been consumed
+ * or dequeued.
+ */
+__bpf_kfunc bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter,
+ struct task_struct *p, u64 dsq_id,
+ u64 enq_flags)
+{
+ return scx_dispatch_from_dsq((struct bpf_iter_scx_dsq_kern *)it__iter,
+ p, dsq_id, enq_flags);
+}
+
+/**
+ * scx_bpf_dispatch_vtime_from_dsq - Move a task from DSQ iteration to a PRIQ DSQ
+ * @it__iter: DSQ iterator in progress
+ * @p: task to transfer
+ * @dsq_id: DSQ to move @p to
+ * @enq_flags: SCX_ENQ_*
+ *
+ * Transfer @p which is on the DSQ currently iterated by @it__iter to the
+ * priority queue of the DSQ specified by @dsq_id. The destination must be a
+ * user DSQ as only user DSQs support priority queue.
+ *
+ * @p's slice and vtime are kept by default. Use
+ * scx_bpf_dispatch_from_dsq_set_slice() and
+ * scx_bpf_dispatch_from_dsq_set_vtime() to update.
+ *
+ * All other aspects are identical to scx_bpf_dispatch_from_dsq(). See
+ * scx_bpf_dispatch_vtime() for more information on @vtime.
+ */
+__bpf_kfunc bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter,
+ struct task_struct *p, u64 dsq_id,
+ u64 enq_flags)
+{
+ return scx_dispatch_from_dsq((struct bpf_iter_scx_dsq_kern *)it__iter,
+ p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_dispatch)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel)
+BTF_ID_FLAGS(func, scx_bpf_consume)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_dispatch)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_dispatch,
+};
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_reenqueue_local - Re-enqueue tasks on a local DSQ
+ *
+ * Iterate over all of the tasks currently enqueued on the local DSQ of the
+ * caller's CPU, and re-enqueue them in the BPF scheduler. Returns the number of
+ * processed tasks. Can only be called from ops.cpu_release().
+ */
+__bpf_kfunc u32 scx_bpf_reenqueue_local(void)
+{
+ LIST_HEAD(tasks);
+ u32 nr_enqueued = 0;
+ struct rq *rq;
+ struct task_struct *p, *n;
+
+ if (!scx_kf_allowed(SCX_KF_CPU_RELEASE))
+ return 0;
+
+ rq = cpu_rq(smp_processor_id());
+ lockdep_assert_rq_held(rq);
+
+ /*
+ * The BPF scheduler may choose to dispatch tasks back to
+ * @rq->scx.local_dsq. Move all candidate tasks off to a private list
+ * first to avoid processing the same tasks repeatedly.
+ */
+ list_for_each_entry_safe(p, n, &rq->scx.local_dsq.list,
+ scx.dsq_list.node) {
+ /*
+ * If @p is being migrated, @p's current CPU may not agree with
+ * its allowed CPUs and the migration_cpu_stop is about to
+ * deactivate and re-activate @p anyway. Skip re-enqueueing.
+ *
+ * While racing sched property changes may also dequeue and
+ * re-enqueue a migrating task while its current CPU and allowed
+ * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to
+ * the current local DSQ for running tasks and thus are not
+ * visible to the BPF scheduler.
+ */
+ if (p->migration_pending)
+ continue;
+
+ dispatch_dequeue(rq, p);
+ list_add_tail(&p->scx.dsq_list.node, &tasks);
+ }
+
+ list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
+ list_del_init(&p->scx.dsq_list.node);
+ do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
+ nr_enqueued++;
+ }
+
+ return nr_enqueued;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_cpu_release)
+BTF_ID_FLAGS(func, scx_bpf_reenqueue_local)
+BTF_KFUNCS_END(scx_kfunc_ids_cpu_release)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_cpu_release = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_cpu_release,
+};
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_create_dsq - Create a custom DSQ
+ * @dsq_id: DSQ to create
+ * @node: NUMA node to allocate from
+ *
+ * Create a custom DSQ identified by @dsq_id. Can be called from any sleepable
+ * scx callback, and any BPF_PROG_TYPE_SYSCALL prog.
+ */
+__bpf_kfunc s32 scx_bpf_create_dsq(u64 dsq_id, s32 node)
+{
+ if (unlikely(node >= (int)nr_node_ids ||
+ (node < 0 && node != NUMA_NO_NODE)))
+ return -EINVAL;
+ return PTR_ERR_OR_ZERO(create_dsq(dsq_id, node));
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_unlocked)
+BTF_ID_FLAGS(func, scx_bpf_create_dsq, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_unlocked)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_unlocked = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_unlocked,
+};
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_kick_cpu - Trigger reschedule on a CPU
+ * @cpu: cpu to kick
+ * @flags: %SCX_KICK_* flags
+ *
+ * Kick @cpu into rescheduling. This can be used to wake up an idle CPU or
+ * trigger rescheduling on a busy CPU. This can be called from any online
+ * scx_ops operation and the actual kicking is performed asynchronously through
+ * an irq work.
+ */
+__bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags)
+{
+ struct rq *this_rq;
+ unsigned long irq_flags;
+
+ if (!ops_cpu_valid(cpu, NULL))
+ return;
+
+ local_irq_save(irq_flags);
+
+ this_rq = this_rq();
+
+ /*
+ * While bypassing for PM ops, IRQ handling may not be online which can
+ * lead to irq_work_queue() malfunction such as infinite busy wait for
+ * IRQ status update. Suppress kicking.
+ */
+ if (scx_rq_bypassing(this_rq))
+ goto out;
+
+ /*
+ * Actual kicking is bounced to kick_cpus_irq_workfn() to avoid nesting
+ * rq locks. We can probably be smarter and avoid bouncing if called
+ * from ops which don't hold a rq lock.
+ */
+ if (flags & SCX_KICK_IDLE) {
+ struct rq *target_rq = cpu_rq(cpu);
+
+ if (unlikely(flags & (SCX_KICK_PREEMPT | SCX_KICK_WAIT)))
+ scx_ops_error("PREEMPT/WAIT cannot be used with SCX_KICK_IDLE");
+
+ if (raw_spin_rq_trylock(target_rq)) {
+ if (can_skip_idle_kick(target_rq)) {
+ raw_spin_rq_unlock(target_rq);
+ goto out;
+ }
+ raw_spin_rq_unlock(target_rq);
+ }
+ cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick_if_idle);
+ } else {
+ cpumask_set_cpu(cpu, this_rq->scx.cpus_to_kick);
+
+ if (flags & SCX_KICK_PREEMPT)
+ cpumask_set_cpu(cpu, this_rq->scx.cpus_to_preempt);
+ if (flags & SCX_KICK_WAIT)
+ cpumask_set_cpu(cpu, this_rq->scx.cpus_to_wait);
+ }
+
+ irq_work_queue(&this_rq->scx.kick_cpus_irq_work);
+out:
+ local_irq_restore(irq_flags);
+}
+
+/**
+ * scx_bpf_dsq_nr_queued - Return the number of queued tasks
+ * @dsq_id: id of the DSQ
+ *
+ * Return the number of tasks in the DSQ matching @dsq_id. If not found,
+ * -%ENOENT is returned.
+ */
+__bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id)
+{
+ struct scx_dispatch_q *dsq;
+ s32 ret;
+
+ preempt_disable();
+
+ if (dsq_id == SCX_DSQ_LOCAL) {
+ ret = READ_ONCE(this_rq()->scx.local_dsq.nr);
+ goto out;
+ } else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) {
+ s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK;
+
+ if (ops_cpu_valid(cpu, NULL)) {
+ ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr);
+ goto out;
+ }
+ } else {
+ dsq = find_user_dsq(dsq_id);
+ if (dsq) {
+ ret = READ_ONCE(dsq->nr);
+ goto out;
+ }
+ }
+ ret = -ENOENT;
+out:
+ preempt_enable();
+ return ret;
+}
+
+/**
+ * scx_bpf_destroy_dsq - Destroy a custom DSQ
+ * @dsq_id: DSQ to destroy
+ *
+ * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with
+ * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is
+ * empty and no further tasks are dispatched to it. Ignored if called on a DSQ
+ * which doesn't exist. Can be called from any online scx_ops operations.
+ */
+__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id)
+{
+ destroy_dsq(dsq_id);
+}
+
+/**
+ * bpf_iter_scx_dsq_new - Create a DSQ iterator
+ * @it: iterator to initialize
+ * @dsq_id: DSQ to iterate
+ * @flags: %SCX_DSQ_ITER_*
+ *
+ * Initialize BPF iterator @it which can be used with bpf_for_each() to walk
+ * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes
+ * tasks which are already queued when this function is invoked.
+ */
+__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id,
+ u64 flags)
+{
+ struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) >
+ sizeof(struct bpf_iter_scx_dsq));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
+ __alignof__(struct bpf_iter_scx_dsq));
+
+ if (flags & ~__SCX_DSQ_ITER_USER_FLAGS)
+ return -EINVAL;
+
+ kit->dsq = find_user_dsq(dsq_id);
+ if (!kit->dsq)
+ return -ENOENT;
+
+ INIT_LIST_HEAD(&kit->cursor.node);
+ kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags;
+ kit->cursor.priv = READ_ONCE(kit->dsq->seq);
+
+ return 0;
+}
+
+/**
+ * bpf_iter_scx_dsq_next - Progress a DSQ iterator
+ * @it: iterator to progress
+ *
+ * Return the next task. See bpf_iter_scx_dsq_new().
+ */
+__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it)
+{
+ struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+ bool rev = kit->cursor.flags & SCX_DSQ_ITER_REV;
+ struct task_struct *p;
+ unsigned long flags;
+
+ if (!kit->dsq)
+ return NULL;
+
+ raw_spin_lock_irqsave(&kit->dsq->lock, flags);
+
+ if (list_empty(&kit->cursor.node))
+ p = NULL;
+ else
+ p = container_of(&kit->cursor, struct task_struct, scx.dsq_list);
+
+ /*
+ * Only tasks which were queued before the iteration started are
+ * visible. This bounds BPF iterations and guarantees that vtime never
+ * jumps in the other direction while iterating.
+ */
+ do {
+ p = nldsq_next_task(kit->dsq, p, rev);
+ } while (p && unlikely(u32_before(kit->cursor.priv, p->scx.dsq_seq)));
+
+ if (p) {
+ if (rev)
+ list_move_tail(&kit->cursor.node, &p->scx.dsq_list.node);
+ else
+ list_move(&kit->cursor.node, &p->scx.dsq_list.node);
+ } else {
+ list_del_init(&kit->cursor.node);
+ }
+
+ raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);
+
+ return p;
+}
+
+/**
+ * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator
+ * @it: iterator to destroy
+ *
+ * Undo scx_iter_scx_dsq_new().
+ */
+__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it)
+{
+ struct bpf_iter_scx_dsq_kern *kit = (void *)it;
+
+ if (!kit->dsq)
+ return;
+
+ if (!list_empty(&kit->cursor.node)) {
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&kit->dsq->lock, flags);
+ list_del_init(&kit->cursor.node);
+ raw_spin_unlock_irqrestore(&kit->dsq->lock, flags);
+ }
+ kit->dsq = NULL;
+}
+
+__bpf_kfunc_end_defs();
+
+static s32 __bstr_format(u64 *data_buf, char *line_buf, size_t line_size,
+ char *fmt, unsigned long long *data, u32 data__sz)
+{
+ struct bpf_bprintf_data bprintf_data = { .get_bin_args = true };
+ s32 ret;
+
+ if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 ||
+ (data__sz && !data)) {
+ scx_ops_error("invalid data=%p and data__sz=%u",
+ (void *)data, data__sz);
+ return -EINVAL;
+ }
+
+ ret = copy_from_kernel_nofault(data_buf, data, data__sz);
+ if (ret < 0) {
+ scx_ops_error("failed to read data fields (%d)", ret);
+ return ret;
+ }
+
+ ret = bpf_bprintf_prepare(fmt, UINT_MAX, data_buf, data__sz / 8,
+ &bprintf_data);
+ if (ret < 0) {
+ scx_ops_error("format preparation failed (%d)", ret);
+ return ret;
+ }
+
+ ret = bstr_printf(line_buf, line_size, fmt,
+ bprintf_data.bin_args);
+ bpf_bprintf_cleanup(&bprintf_data);
+ if (ret < 0) {
+ scx_ops_error("(\"%s\", %p, %u) failed to format",
+ fmt, data, data__sz);
+ return ret;
+ }
+
+ return ret;
+}
+
+static s32 bstr_format(struct scx_bstr_buf *buf,
+ char *fmt, unsigned long long *data, u32 data__sz)
+{
+ return __bstr_format(buf->data, buf->line, sizeof(buf->line),
+ fmt, data, data__sz);
+}
+
+__bpf_kfunc_start_defs();
+
+/**
+ * scx_bpf_exit_bstr - Gracefully exit the BPF scheduler.
+ * @exit_code: Exit value to pass to user space via struct scx_exit_info.
+ * @fmt: error message format string
+ * @data: format string parameters packaged using ___bpf_fill() macro
+ * @data__sz: @data len, must end in '__sz' for the verifier
+ *
+ * Indicate that the BPF scheduler wants to exit gracefully, and initiate ops
+ * disabling.
+ */
+__bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt,
+ unsigned long long *data, u32 data__sz)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
+ if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
+ scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s",
+ scx_exit_bstr_buf.line);
+ raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
+}
+
+/**
+ * scx_bpf_error_bstr - Indicate fatal error
+ * @fmt: error message format string
+ * @data: format string parameters packaged using ___bpf_fill() macro
+ * @data__sz: @data len, must end in '__sz' for the verifier
+ *
+ * Indicate that the BPF scheduler encountered a fatal error and initiate ops
+ * disabling.
+ */
+__bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data,
+ u32 data__sz)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&scx_exit_bstr_buf_lock, flags);
+ if (bstr_format(&scx_exit_bstr_buf, fmt, data, data__sz) >= 0)
+ scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s",
+ scx_exit_bstr_buf.line);
+ raw_spin_unlock_irqrestore(&scx_exit_bstr_buf_lock, flags);
+}
+
+/**
+ * scx_bpf_dump - Generate extra debug dump specific to the BPF scheduler
+ * @fmt: format string
+ * @data: format string parameters packaged using ___bpf_fill() macro
+ * @data__sz: @data len, must end in '__sz' for the verifier
+ *
+ * To be called through scx_bpf_dump() helper from ops.dump(), dump_cpu() and
+ * dump_task() to generate extra debug dump specific to the BPF scheduler.
+ *
+ * The extra dump may be multiple lines. A single line may be split over
+ * multiple calls. The last line is automatically terminated.
+ */
+__bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data,
+ u32 data__sz)
+{
+ struct scx_dump_data *dd = &scx_dump_data;
+ struct scx_bstr_buf *buf = &dd->buf;
+ s32 ret;
+
+ if (raw_smp_processor_id() != dd->cpu) {
+ scx_ops_error("scx_bpf_dump() must only be called from ops.dump() and friends");
+ return;
+ }
+
+ /* append the formatted string to the line buf */
+ ret = __bstr_format(buf->data, buf->line + dd->cursor,
+ sizeof(buf->line) - dd->cursor, fmt, data, data__sz);
+ if (ret < 0) {
+ dump_line(dd->s, "%s[!] (\"%s\", %p, %u) failed to format (%d)",
+ dd->prefix, fmt, data, data__sz, ret);
+ return;
+ }
+
+ dd->cursor += ret;
+ dd->cursor = min_t(s32, dd->cursor, sizeof(buf->line));
+
+ if (!dd->cursor)
+ return;
+
+ /*
+ * If the line buf overflowed or ends in a newline, flush it into the
+ * dump. This is to allow the caller to generate a single line over
+ * multiple calls. As ops_dump_flush() can also handle multiple lines in
+ * the line buf, the only case which can lead to an unexpected
+ * truncation is when the caller keeps generating newlines in the middle
+ * instead of the end consecutively. Don't do that.
+ */
+ if (dd->cursor >= sizeof(buf->line) || buf->line[dd->cursor - 1] == '\n')
+ ops_dump_flush();
+}
+
+/**
+ * scx_bpf_cpuperf_cap - Query the maximum relative capacity of a CPU
+ * @cpu: CPU of interest
+ *
+ * Return the maximum relative capacity of @cpu in relation to the most
+ * performant CPU in the system. The return value is in the range [1,
+ * %SCX_CPUPERF_ONE]. See scx_bpf_cpuperf_cur().
+ */
+__bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
+{
+ if (ops_cpu_valid(cpu, NULL))
+ return arch_scale_cpu_capacity(cpu);
+ else
+ return SCX_CPUPERF_ONE;
+}
+
+/**
+ * scx_bpf_cpuperf_cur - Query the current relative performance of a CPU
+ * @cpu: CPU of interest
+ *
+ * Return the current relative performance of @cpu in relation to its maximum.
+ * The return value is in the range [1, %SCX_CPUPERF_ONE].
+ *
+ * The current performance level of a CPU in relation to the maximum performance
+ * available in the system can be calculated as follows:
+ *
+ * scx_bpf_cpuperf_cap() * scx_bpf_cpuperf_cur() / %SCX_CPUPERF_ONE
+ *
+ * The result is in the range [1, %SCX_CPUPERF_ONE].
+ */
+__bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
+{
+ if (ops_cpu_valid(cpu, NULL))
+ return arch_scale_freq_capacity(cpu);
+ else
+ return SCX_CPUPERF_ONE;
+}
+
+/**
+ * scx_bpf_cpuperf_set - Set the relative performance target of a CPU
+ * @cpu: CPU of interest
+ * @perf: target performance level [0, %SCX_CPUPERF_ONE]
+ * @flags: %SCX_CPUPERF_* flags
+ *
+ * Set the target performance level of @cpu to @perf. @perf is in linear
+ * relative scale between 0 and %SCX_CPUPERF_ONE. This determines how the
+ * schedutil cpufreq governor chooses the target frequency.
+ *
+ * The actual performance level chosen, CPU grouping, and the overhead and
+ * latency of the operations are dependent on the hardware and cpufreq driver in
+ * use. Consult hardware and cpufreq documentation for more information. The
+ * current performance level can be monitored using scx_bpf_cpuperf_cur().
+ */
+__bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
+{
+ if (unlikely(perf > SCX_CPUPERF_ONE)) {
+ scx_ops_error("Invalid cpuperf target %u for CPU %d", perf, cpu);
+ return;
+ }
+
+ if (ops_cpu_valid(cpu, NULL)) {
+ struct rq *rq = cpu_rq(cpu);
+
+ rq->scx.cpuperf_target = perf;
+
+ rcu_read_lock_sched_notrace();
+ cpufreq_update_util(cpu_rq(cpu), 0);
+ rcu_read_unlock_sched_notrace();
+ }
+}
+
+/**
+ * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs
+ *
+ * All valid CPU IDs in the system are smaller than the returned value.
+ */
+__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void)
+{
+ return nr_cpu_ids;
+}
+
+/**
+ * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_possible_cpumask(void)
+{
+ return cpu_possible_mask;
+}
+
+/**
+ * scx_bpf_get_online_cpumask - Get a referenced kptr to cpu_online_mask
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_online_cpumask(void)
+{
+ return cpu_online_mask;
+}
+
+/**
+ * scx_bpf_put_cpumask - Release a possible/online cpumask
+ * @cpumask: cpumask to release
+ */
+__bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask)
+{
+ /*
+ * Empty function body because we aren't actually acquiring or releasing
+ * a reference to a global cpumask, which is read-only in the caller and
+ * is never released. The acquire / release semantics here are just used
+ * to make the cpumask is a trusted pointer in the caller.
+ */
+}
+
+/**
+ * scx_bpf_get_idle_cpumask - Get a referenced kptr to the idle-tracking
+ * per-CPU cpumask.
+ *
+ * Returns NULL if idle tracking is not enabled, or running on a UP kernel.
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_idle_cpumask(void)
+{
+ if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+ scx_ops_error("built-in idle tracking is disabled");
+ return cpu_none_mask;
+ }
+
+#ifdef CONFIG_SMP
+ return idle_masks.cpu;
+#else
+ return cpu_none_mask;
+#endif
+}
+
+/**
+ * scx_bpf_get_idle_smtmask - Get a referenced kptr to the idle-tracking,
+ * per-physical-core cpumask. Can be used to determine if an entire physical
+ * core is free.
+ *
+ * Returns NULL if idle tracking is not enabled, or running on a UP kernel.
+ */
+__bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void)
+{
+ if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+ scx_ops_error("built-in idle tracking is disabled");
+ return cpu_none_mask;
+ }
+
+#ifdef CONFIG_SMP
+ if (sched_smt_active())
+ return idle_masks.smt;
+ else
+ return idle_masks.cpu;
+#else
+ return cpu_none_mask;
+#endif
+}
+
+/**
+ * scx_bpf_put_idle_cpumask - Release a previously acquired referenced kptr to
+ * either the percpu, or SMT idle-tracking cpumask.
+ */
+__bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask)
+{
+ /*
+ * Empty function body because we aren't actually acquiring or releasing
+ * a reference to a global idle cpumask, which is read-only in the
+ * caller and is never released. The acquire / release semantics here
+ * are just used to make the cpumask a trusted pointer in the caller.
+ */
+}
+
+/**
+ * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state
+ * @cpu: cpu to test and clear idle for
+ *
+ * Returns %true if @cpu was idle and its idle state was successfully cleared.
+ * %false otherwise.
+ *
+ * Unavailable if ops.update_idle() is implemented and
+ * %SCX_OPS_KEEP_BUILTIN_IDLE is not set.
+ */
+__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu)
+{
+ if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+ scx_ops_error("built-in idle tracking is disabled");
+ return false;
+ }
+
+ if (ops_cpu_valid(cpu, NULL))
+ return test_and_clear_cpu_idle(cpu);
+ else
+ return false;
+}
+
+/**
+ * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu
+ * @cpus_allowed: Allowed cpumask
+ * @flags: %SCX_PICK_IDLE_CPU_* flags
+ *
+ * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu
+ * number on success. -%EBUSY if no matching cpu was found.
+ *
+ * Idle CPU tracking may race against CPU scheduling state transitions. For
+ * example, this function may return -%EBUSY as CPUs are transitioning into the
+ * idle state. If the caller then assumes that there will be dispatch events on
+ * the CPUs as they were all busy, the scheduler may end up stalling with CPUs
+ * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and
+ * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch
+ * event in the near future.
+ *
+ * Unavailable if ops.update_idle() is implemented and
+ * %SCX_OPS_KEEP_BUILTIN_IDLE is not set.
+ */
+__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed,
+ u64 flags)
+{
+ if (!static_branch_likely(&scx_builtin_idle_enabled)) {
+ scx_ops_error("built-in idle tracking is disabled");
+ return -EBUSY;
+ }
+
+ return scx_pick_idle_cpu(cpus_allowed, flags);
+}
+
+/**
+ * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU
+ * @cpus_allowed: Allowed cpumask
+ * @flags: %SCX_PICK_IDLE_CPU_* flags
+ *
+ * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any
+ * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu
+ * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is
+ * empty.
+ *
+ * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not
+ * set, this function can't tell which CPUs are idle and will always pick any
+ * CPU.
+ */
+__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed,
+ u64 flags)
+{
+ s32 cpu;
+
+ if (static_branch_likely(&scx_builtin_idle_enabled)) {
+ cpu = scx_pick_idle_cpu(cpus_allowed, flags);
+ if (cpu >= 0)
+ return cpu;
+ }
+
+ cpu = cpumask_any_distribute(cpus_allowed);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+ else
+ return -EBUSY;
+}
+
+/**
+ * scx_bpf_task_running - Is task currently running?
+ * @p: task of interest
+ */
+__bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p)
+{
+ return task_rq(p)->curr == p;
+}
+
+/**
+ * scx_bpf_task_cpu - CPU a task is currently associated with
+ * @p: task of interest
+ */
+__bpf_kfunc s32 scx_bpf_task_cpu(const struct task_struct *p)
+{
+ return task_cpu(p);
+}
+
+/**
+ * scx_bpf_cpu_rq - Fetch the rq of a CPU
+ * @cpu: CPU of the rq
+ */
+__bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
+{
+ if (!ops_cpu_valid(cpu, NULL))
+ return NULL;
+
+ return cpu_rq(cpu);
+}
+
+/**
+ * scx_bpf_task_cgroup - Return the sched cgroup of a task
+ * @p: task of interest
+ *
+ * @p->sched_task_group->css.cgroup represents the cgroup @p is associated with
+ * from the scheduler's POV. SCX operations should use this function to
+ * determine @p's current cgroup as, unlike following @p->cgroups,
+ * @p->sched_task_group is protected by @p's rq lock and thus atomic w.r.t. all
+ * rq-locked operations. Can be called on the parameter tasks of rq-locked
+ * operations. The restriction guarantees that @p's rq is locked by the caller.
+ */
+#ifdef CONFIG_CGROUP_SCHED
+__bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p)
+{
+ struct task_group *tg = p->sched_task_group;
+ struct cgroup *cgrp = &cgrp_dfl_root.cgrp;
+
+ if (!scx_kf_allowed_on_arg_tasks(__SCX_KF_RQ_LOCKED, p))
+ goto out;
+
+ /*
+ * A task_group may either be a cgroup or an autogroup. In the latter
+ * case, @tg->css.cgroup is %NULL. A task_group can't become the other
+ * kind once created.
+ */
+ if (tg && tg->css.cgroup)
+ cgrp = tg->css.cgroup;
+ else
+ cgrp = &cgrp_dfl_root.cgrp;
+out:
+ cgroup_get(cgrp);
+ return cgrp;
+}
+#endif
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(scx_kfunc_ids_any)
+BTF_ID_FLAGS(func, scx_bpf_kick_cpu)
+BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued)
+BTF_ID_FLAGS(func, scx_bpf_destroy_dsq)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur)
+BTF_ID_FLAGS(func, scx_bpf_cpuperf_set)
+BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids)
+BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE)
+BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE)
+BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle)
+BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
+#ifdef CONFIG_CGROUP_SCHED
+BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
+#endif
+BTF_KFUNCS_END(scx_kfunc_ids_any)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_any = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_any,
+};
+
+static int __init scx_init(void)
+{
+ int ret;
+
+ /*
+ * kfunc registration can't be done from init_sched_ext_class() as
+ * register_btf_kfunc_id_set() needs most of the system to be up.
+ *
+ * Some kfuncs are context-sensitive and can only be called from
+ * specific SCX ops. They are grouped into BTF sets accordingly.
+ * Unfortunately, BPF currently doesn't have a way of enforcing such
+ * restrictions. Eventually, the verifier should be able to enforce
+ * them. For now, register them the same and make each kfunc explicitly
+ * check using scx_kf_allowed().
+ */
+ if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_select_cpu)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_enqueue_dispatch)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_dispatch)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_cpu_release)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_unlocked)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL,
+ &scx_kfunc_set_unlocked)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_any)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+ &scx_kfunc_set_any)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL,
+ &scx_kfunc_set_any))) {
+ pr_err("sched_ext: Failed to register kfunc sets (%d)\n", ret);
+ return ret;
+ }
+
+ ret = register_bpf_struct_ops(&bpf_sched_ext_ops, sched_ext_ops);
+ if (ret) {
+ pr_err("sched_ext: Failed to register struct_ops (%d)\n", ret);
+ return ret;
+ }
+
+ ret = register_pm_notifier(&scx_pm_notifier);
+ if (ret) {
+ pr_err("sched_ext: Failed to register PM notifier (%d)\n", ret);
+ return ret;
+ }
+
+ scx_kset = kset_create_and_add("sched_ext", &scx_uevent_ops, kernel_kobj);
+ if (!scx_kset) {
+ pr_err("sched_ext: Failed to create /sys/kernel/sched_ext\n");
+ return -ENOMEM;
+ }
+
+ ret = sysfs_create_group(&scx_kset->kobj, &scx_global_attr_group);
+ if (ret < 0) {
+ pr_err("sched_ext: Failed to add global attributes\n");
+ return ret;
+ }
+
+ return 0;
+}
+__initcall(scx_init);
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
new file mode 100644
index 000000000000..246019519231
--- /dev/null
+++ b/kernel/sched/ext.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
+ *
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2022 Tejun Heo <tj@kernel.org>
+ * Copyright (c) 2022 David Vernet <dvernet@meta.com>
+ */
+#ifdef CONFIG_SCHED_CLASS_EXT
+
+void scx_tick(struct rq *rq);
+void init_scx_entity(struct sched_ext_entity *scx);
+void scx_pre_fork(struct task_struct *p);
+int scx_fork(struct task_struct *p);
+void scx_post_fork(struct task_struct *p);
+void scx_cancel_fork(struct task_struct *p);
+bool scx_can_stop_tick(struct rq *rq);
+void scx_rq_activate(struct rq *rq);
+void scx_rq_deactivate(struct rq *rq);
+int scx_check_setscheduler(struct task_struct *p, int policy);
+bool task_should_scx(struct task_struct *p);
+void init_sched_ext_class(void);
+
+static inline u32 scx_cpuperf_target(s32 cpu)
+{
+ if (scx_enabled())
+ return cpu_rq(cpu)->scx.cpuperf_target;
+ else
+ return 0;
+}
+
+static inline bool task_on_scx(const struct task_struct *p)
+{
+ return scx_enabled() && p->sched_class == &ext_sched_class;
+}
+
+#ifdef CONFIG_SCHED_CORE
+bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
+ bool in_fi);
+#endif
+
+#else /* CONFIG_SCHED_CLASS_EXT */
+
+static inline void scx_tick(struct rq *rq) {}
+static inline void scx_pre_fork(struct task_struct *p) {}
+static inline int scx_fork(struct task_struct *p) { return 0; }
+static inline void scx_post_fork(struct task_struct *p) {}
+static inline void scx_cancel_fork(struct task_struct *p) {}
+static inline u32 scx_cpuperf_target(s32 cpu) { return 0; }
+static inline bool scx_can_stop_tick(struct rq *rq) { return true; }
+static inline void scx_rq_activate(struct rq *rq) {}
+static inline void scx_rq_deactivate(struct rq *rq) {}
+static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
+static inline bool task_on_scx(const struct task_struct *p) { return false; }
+static inline void init_sched_ext_class(void) {}
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
+#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
+void __scx_update_idle(struct rq *rq, bool idle);
+
+static inline void scx_update_idle(struct rq *rq, bool idle)
+{
+ if (scx_enabled())
+ __scx_update_idle(rq, idle);
+}
+#else
+static inline void scx_update_idle(struct rq *rq, bool idle) {}
+#endif
+
+#ifdef CONFIG_CGROUP_SCHED
+#ifdef CONFIG_EXT_GROUP_SCHED
+int scx_tg_online(struct task_group *tg);
+void scx_tg_offline(struct task_group *tg);
+int scx_cgroup_can_attach(struct cgroup_taskset *tset);
+void scx_move_task(struct task_struct *p);
+void scx_cgroup_finish_attach(void);
+void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
+void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
+void scx_group_set_idle(struct task_group *tg, bool idle);
+#else /* CONFIG_EXT_GROUP_SCHED */
+static inline int scx_tg_online(struct task_group *tg) { return 0; }
+static inline void scx_tg_offline(struct task_group *tg) {}
+static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
+static inline void scx_move_task(struct task_struct *p) {}
+static inline void scx_cgroup_finish_attach(void) {}
+static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {}
+static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {}
+static inline void scx_group_set_idle(struct task_group *tg, bool idle) {}
+#endif /* CONFIG_EXT_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 91b242e47db7..a36e37a674e8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3857,7 +3857,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
}
}
-void reweight_task(struct task_struct *p, const struct load_weight *lw)
+static void reweight_task_fair(struct rq *rq, struct task_struct *p,
+ const struct load_weight *lw)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -9365,29 +9366,18 @@ static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {
static bool __update_blocked_others(struct rq *rq, bool *done)
{
- const struct sched_class *curr_class;
- u64 now = rq_clock_pelt(rq);
- unsigned long hw_pressure;
- bool decayed;
+ bool updated;
/*
* update_load_avg() can call cpufreq_update_util(). Make sure that RT,
* DL and IRQ signals have been updated before updating CFS.
*/
- curr_class = rq->curr->sched_class;
-
- hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
-
- /* hw_pressure doesn't care about invariance */
- decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
- update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
- update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
- update_irq_load_avg(rq, 0);
+ updated = update_other_load_avgs(rq);
if (others_have_blocked(rq))
*done = false;
- return decayed;
+ return updated;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -13233,6 +13223,7 @@ DEFINE_SCHED_CLASS(fair) = {
.task_tick = task_tick_fair,
.task_fork = task_fork_fair,
+ .reweight_task = reweight_task_fair,
.prio_changed = prio_changed_fair,
.switched_from = switched_from_fair,
.switched_to = switched_to_fair,
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6e78d071beb5..c7a218123b7a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -452,11 +452,13 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
{
+ scx_update_idle(rq, false);
}
static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
{
update_idle_core(rq);
+ scx_update_idle(rq, true);
schedstat_inc(rq->sched_goidle);
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 432b43aa091c..48d893de632b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -192,9 +192,18 @@ static inline int idle_policy(int policy)
return policy == SCHED_IDLE;
}
+static inline int normal_policy(int policy)
+{
+#ifdef CONFIG_SCHED_CLASS_EXT
+ if (policy == SCHED_EXT)
+ return true;
+#endif
+ return policy == SCHED_NORMAL;
+}
+
static inline int fair_policy(int policy)
{
- return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+ return normal_policy(policy) || policy == SCHED_BATCH;
}
static inline int rt_policy(int policy)
@@ -244,6 +253,24 @@ static inline void update_avg(u64 *avg, u64 sample)
#define shr_bound(val, shift) \
(val >> min_t(typeof(shift), shift, BITS_PER_TYPE(typeof(val)) - 1))
+/*
+ * cgroup weight knobs should use the common MIN, DFL and MAX values which are
+ * 1, 100 and 10000 respectively. While it loses a bit of range on both ends, it
+ * maps pretty well onto the shares value used by scheduler and the round-trip
+ * conversions preserve the original value over the entire range.
+ */
+static inline unsigned long sched_weight_from_cgroup(unsigned long cgrp_weight)
+{
+ return DIV_ROUND_CLOSEST_ULL(cgrp_weight * 1024, CGROUP_WEIGHT_DFL);
+}
+
+static inline unsigned long sched_weight_to_cgroup(unsigned long weight)
+{
+ return clamp_t(unsigned long,
+ DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024),
+ CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
+}
+
/*
* !! For sched_setattr_nocheck() (kernel) only !!
*
@@ -397,16 +424,17 @@ struct cfs_bandwidth {
struct task_group {
struct cgroup_subsys_state css;
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
+ /* A positive value indicates that this is a SCHED_IDLE group. */
+ int idle;
+#endif
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each CPU */
struct sched_entity **se;
/* runqueue "owned" by this group on each CPU */
struct cfs_rq **cfs_rq;
unsigned long shares;
-
- /* A positive value indicates that this is a SCHED_IDLE group. */
- int idle;
-
#ifdef CONFIG_SMP
/*
* load_avg can be heavily contended at clock tick time, so put
@@ -424,6 +452,11 @@ struct task_group {
struct rt_bandwidth rt_bandwidth;
#endif
+#ifdef CONFIG_EXT_GROUP_SCHED
+ u32 scx_flags; /* SCX_TG_* */
+ u32 scx_weight;
+#endif
+
struct rcu_head rcu;
struct list_head list;
@@ -448,7 +481,7 @@ struct task_group {
};
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED_WEIGHT
#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
/*
@@ -479,6 +512,11 @@ static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
return walk_tg_tree_from(&root_task_group, down, up, data);
}
+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
+{
+ return css ? container_of(css, struct task_group, css) : NULL;
+}
+
extern int tg_nop(struct task_group *tg, void *data);
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -535,6 +573,9 @@ extern void set_task_rq_fair(struct sched_entity *se,
static inline void set_task_rq_fair(struct sched_entity *se,
struct cfs_rq *prev, struct cfs_rq *next) { }
#endif /* CONFIG_SMP */
+#else /* !CONFIG_FAIR_GROUP_SCHED */
+static inline int sched_group_set_shares(struct task_group *tg, unsigned long shares) { return 0; }
+static inline int sched_group_set_idle(struct task_group *tg, long idle) { return 0; }
#endif /* CONFIG_FAIR_GROUP_SCHED */
#else /* CONFIG_CGROUP_SCHED */
@@ -588,6 +629,11 @@ do { \
# define u64_u32_load(var) u64_u32_load_copy(var, var##_copy)
# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val)
+struct balance_callback {
+ struct balance_callback *next;
+ void (*func)(struct rq *rq);
+};
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
@@ -696,6 +742,43 @@ struct cfs_rq {
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
+#ifdef CONFIG_SCHED_CLASS_EXT
+/* scx_rq->flags, protected by the rq lock */
+enum scx_rq_flags {
+ /*
+ * A hotplugged CPU starts scheduling before rq_online_scx(). Track
+ * ops.cpu_on/offline() state so that ops.enqueue/dispatch() are called
+ * only while the BPF scheduler considers the CPU to be online.
+ */
+ SCX_RQ_ONLINE = 1 << 0,
+ SCX_RQ_CAN_STOP_TICK = 1 << 1,
+ SCX_RQ_BYPASSING = 1 << 3,
+
+ SCX_RQ_IN_WAKEUP = 1 << 16,
+ SCX_RQ_IN_BALANCE = 1 << 17,
+};
+
+struct scx_rq {
+ struct scx_dispatch_q local_dsq;
+ struct list_head runnable_list; /* runnable tasks on this rq */
+ struct list_head ddsp_deferred_locals; /* deferred ddsps from enq */
+ unsigned long ops_qseq;
+ u64 extra_enq_flags; /* see move_task_to_local_dsq() */
+ u32 nr_running;
+ u32 flags;
+ u32 cpuperf_target; /* [0, SCHED_CAPACITY_SCALE] */
+ bool cpu_released;
+ cpumask_var_t cpus_to_kick;
+ cpumask_var_t cpus_to_kick_if_idle;
+ cpumask_var_t cpus_to_preempt;
+ cpumask_var_t cpus_to_wait;
+ unsigned long pnt_seq;
+ struct balance_callback deferred_bal_cb;
+ struct irq_work deferred_irq_work;
+ struct irq_work kick_cpus_irq_work;
+};
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
static inline int rt_bandwidth_enabled(void)
{
return sysctl_sched_rt_runtime >= 0;
@@ -996,11 +1079,6 @@ struct uclamp_rq {
DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
#endif /* CONFIG_UCLAMP_TASK */
-struct balance_callback {
- struct balance_callback *next;
- void (*func)(struct rq *rq);
-};
-
/*
* This is the main, per-CPU runqueue data structure.
*
@@ -1043,6 +1121,9 @@ struct rq {
struct cfs_rq cfs;
struct rt_rq rt;
struct dl_rq dl;
+#ifdef CONFIG_SCHED_CLASS_EXT
+ struct scx_rq scx;
+#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this CPU: */
@@ -2291,13 +2372,15 @@ struct sched_class {
void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
+ int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
struct task_struct *(*pick_next_task)(struct rq *rq);
void (*put_prev_task)(struct rq *rq, struct task_struct *p);
void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
+ void (*switch_class)(struct rq *rq, struct task_struct *next);
+
#ifdef CONFIG_SMP
- int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
int (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
struct task_struct * (*pick_task)(struct rq *rq);
@@ -2323,8 +2406,11 @@ struct sched_class {
* cannot assume the switched_from/switched_to pair is serialized by
* rq->lock. They are however serialized by p->pi_lock.
*/
+ void (*switching_to) (struct rq *this_rq, struct task_struct *task);
void (*switched_from)(struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
+ void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
+ const struct load_weight *lw);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio);
@@ -2373,19 +2459,54 @@ const struct sched_class name##_sched_class \
extern struct sched_class __sched_class_highest[];
extern struct sched_class __sched_class_lowest[];
+extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
+extern const struct sched_class rt_sched_class;
+extern const struct sched_class fair_sched_class;
+extern const struct sched_class idle_sched_class;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+extern const struct sched_class ext_sched_class;
+
+DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled); /* SCX BPF scheduler loaded */
+DECLARE_STATIC_KEY_FALSE(__scx_switched_all); /* all fair class tasks on SCX */
+
+#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled)
+#define scx_switched_all() static_branch_unlikely(&__scx_switched_all)
+#else /* !CONFIG_SCHED_CLASS_EXT */
+#define scx_enabled() false
+#define scx_switched_all() false
+#endif /* !CONFIG_SCHED_CLASS_EXT */
+
+/*
+ * Iterate only active classes. SCX can take over all fair tasks or be
+ * completely disabled. If the former, skip fair. If the latter, skip SCX.
+ */
+static inline const struct sched_class *next_active_class(const struct sched_class *class)
+{
+ class++;
+#ifdef CONFIG_SCHED_CLASS_EXT
+ if (scx_switched_all() && class == &fair_sched_class)
+ class++;
+ if (!scx_enabled() && class == &ext_sched_class)
+ class++;
+#endif
+ return class;
+}
+
#define for_class_range(class, _from, _to) \
for (class = (_from); class < (_to); class++)
#define for_each_class(class) \
for_class_range(class, __sched_class_highest, __sched_class_lowest)
-#define sched_class_above(_a, _b) ((_a) < (_b))
+#define for_active_class_range(class, _from, _to) \
+ for (class = (_from); class != (_to); class = next_active_class(class))
-extern const struct sched_class stop_sched_class;
-extern const struct sched_class dl_sched_class;
-extern const struct sched_class rt_sched_class;
-extern const struct sched_class fair_sched_class;
-extern const struct sched_class idle_sched_class;
+#define for_each_active_class(class) \
+ for_active_class_range(class, __sched_class_highest, __sched_class_lowest)
+
+#define sched_class_above(_a, _b) ((_a) < (_b))
static inline bool sched_stop_runnable(struct rq *rq)
{
@@ -2424,6 +2545,19 @@ extern void sched_balance_trigger(struct rq *rq);
extern int __set_cpus_allowed_ptr(struct task_struct *p, struct affinity_context *ctx);
extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx);
+static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
+{
+ /* When not in the task's cpumask, no point in looking further. */
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+ return false;
+
+ /* Can @cpu run a user thread? */
+ if (!(p->flags & PF_KTHREAD) && !task_cpu_possible(cpu, p))
+ return false;
+
+ return true;
+}
+
static inline cpumask_t *alloc_user_cpus_ptr(int node)
{
/*
@@ -2457,6 +2591,11 @@ extern int push_cpu_stop(void *arg);
#else /* !CONFIG_SMP: */
+static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
+{
+ return true;
+}
+
static inline int __set_cpus_allowed_ptr(struct task_struct *p,
struct affinity_context *ctx)
{
@@ -2510,8 +2649,6 @@ extern void init_sched_dl_class(void);
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
-extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
-
extern void resched_curr(struct rq *rq);
extern void resched_cpu(int cpu);
@@ -3056,6 +3193,8 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) { }
#ifdef CONFIG_SMP
+bool update_other_load_avgs(struct rq *rq);
+
unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
unsigned long *min,
unsigned long *max);
@@ -3099,6 +3238,8 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
return READ_ONCE(rq->avg_rt.util_avg);
}
+#else /* !CONFIG_SMP */
+static inline bool update_other_load_avgs(struct rq *rq) { return false; }
#endif /* CONFIG_SMP */
#ifdef CONFIG_UCLAMP_TASK
@@ -3609,6 +3750,8 @@ extern void set_load_weight(struct task_struct *p, bool update_load);
extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags);
extern void dequeue_task(struct rq *rq, struct task_struct *p, int flags);
+extern void check_class_changing(struct rq *rq, struct task_struct *p,
+ const struct sched_class *prev_class);
extern void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
int oldprio);
@@ -3629,4 +3772,24 @@ static inline void balance_callbacks(struct rq *rq, struct balance_callback *hea
#endif
+#ifdef CONFIG_SCHED_CLASS_EXT
+/*
+ * Used by SCX in the enable/disable paths to move tasks between sched_classes
+ * and establish invariants.
+ */
+struct sched_enq_and_set_ctx {
+ struct task_struct *p;
+ int queue_flags;
+ bool queued;
+ bool running;
+};
+
+void sched_deq_and_put_task(struct task_struct *p, int queue_flags,
+ struct sched_enq_and_set_ctx *ctx);
+void sched_enq_and_set_task(struct sched_enq_and_set_ctx *ctx);
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
+#include "ext.h"
+
#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index ae1b42775ef9..4fa59c9f69ac 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -259,6 +259,25 @@ int sched_core_idle_cpu(int cpu)
#endif
#ifdef CONFIG_SMP
+/*
+ * Load avg and utiliztion metrics need to be updated periodically and before
+ * consumption. This function updates the metrics for all subsystems except for
+ * the fair class. @rq must be locked and have its clock updated.
+ */
+bool update_other_load_avgs(struct rq *rq)
+{
+ u64 now = rq_clock_pelt(rq);
+ const struct sched_class *curr_class = rq->curr->sched_class;
+ unsigned long hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
+
+ lockdep_assert_rq_held(rq);
+
+ return update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+ update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+ update_hw_load_avg(now, rq, hw_pressure) |
+ update_irq_load_avg(rq, 0);
+}
+
/*
* This function computes an effective utilization for the given CPU, to be
* used for frequency selection given the linear relation: f = u * f_max.
@@ -695,6 +714,10 @@ int __sched_setscheduler(struct task_struct *p,
goto unlock;
}
+ retval = scx_check_setscheduler(p, policy);
+ if (retval)
+ goto unlock;
+
/*
* If not changing anything there's no need to proceed further,
* but store a possible modification of reset_on_fork.
@@ -797,6 +820,7 @@ int __sched_setscheduler(struct task_struct *p,
__setscheduler_prio(p, newprio);
}
__setscheduler_uclamp(p, attr);
+ check_class_changing(rq, p, prev_class);
if (queued) {
/*
@@ -1602,6 +1626,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
+ case SCHED_EXT:
ret = 0;
break;
}
@@ -1629,6 +1654,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
+ case SCHED_EXT:
ret = 0;
}
return ret;
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 1a996fbbf50a..388da1aea14a 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -73,6 +73,7 @@ void dump_stack_print_info(const char *log_lvl)
print_worker_info(log_lvl, current);
print_stop_info(log_lvl, current);
+ print_scx_info(log_lvl, current);
}
/**
diff --git a/tools/Makefile b/tools/Makefile
index 276f5d0d53a4..278d24723b74 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -28,6 +28,7 @@ help:
@echo ' pci - PCI tools'
@echo ' perf - Linux performance measurement and analysis tool'
@echo ' selftests - various kernel selftests'
+ @echo ' sched_ext - sched_ext example schedulers'
@echo ' bootconfig - boot config tool'
@echo ' spi - spi tools'
@echo ' tmon - thermal monitoring and tuning tool'
@@ -91,6 +92,9 @@ perf: FORCE
$(Q)mkdir -p $(PERF_O) .
$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
+sched_ext: FORCE
+ $(call descend,sched_ext)
+
selftests: FORCE
$(call descend,testing/$@)
@@ -184,6 +188,9 @@ perf_clean:
$(Q)mkdir -p $(PERF_O) .
$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= clean
+sched_ext_clean:
+ $(call descend,sched_ext,clean)
+
selftests_clean:
$(call descend,testing/$(@:_clean=),clean)
@@ -213,6 +220,7 @@ clean: acpi_clean counter_clean cpupower_clean hv_clean firewire_clean \
mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
freefall_clean build_clean libbpf_clean libsubcmd_clean \
gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
- intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean
+ intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean \
+ sched_ext_clean
.PHONY: FORCE
diff --git a/tools/sched_ext/.gitignore b/tools/sched_ext/.gitignore
new file mode 100644
index 000000000000..d6264fe1c8cd
--- /dev/null
+++ b/tools/sched_ext/.gitignore
@@ -0,0 +1,2 @@
+tools/
+build/
diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile
new file mode 100644
index 000000000000..ca3815e572d8
--- /dev/null
+++ b/tools/sched_ext/Makefile
@@ -0,0 +1,246 @@
+# 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
+
+all: all_targets
+
+ifneq ($(LLVM),)
+ifneq ($(filter %/,$(LLVM)),)
+LLVM_PREFIX := $(LLVM)
+else ifneq ($(filter -%,$(LLVM)),)
+LLVM_SUFFIX := $(LLVM)
+endif
+
+CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi
+CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu
+CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl
+CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu
+CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu
+CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu
+CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu
+CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu
+CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu
+CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH))
+
+ifeq ($(CROSS_COMPILE),)
+ifeq ($(CLANG_TARGET_FLAGS),)
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk)
+else
+CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS)
+endif # CLANG_TARGET_FLAGS
+else
+CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif # CROSS_COMPILE
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+else
+CC := $(CROSS_COMPILE)gcc
+endif # LLVM
+
+CURDIR := $(abspath .)
+TOOLSDIR := $(abspath ..)
+LIBDIR := $(TOOLSDIR)/lib
+BPFDIR := $(LIBDIR)/bpf
+TOOLSINCDIR := $(TOOLSDIR)/include
+BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
+APIDIR := $(TOOLSINCDIR)/uapi
+GENDIR := $(abspath ../../include/generated)
+GENHDR := $(GENDIR)/autoconf.h
+
+ifeq ($(O),)
+OUTPUT_DIR := $(CURDIR)/build
+else
+OUTPUT_DIR := $(O)/build
+endif # O
+OBJ_DIR := $(OUTPUT_DIR)/obj
+INCLUDE_DIR := $(OUTPUT_DIR)/include
+BPFOBJ_DIR := $(OBJ_DIR)/libbpf
+SCXOBJ_DIR := $(OBJ_DIR)/sched_ext
+BINDIR := $(OUTPUT_DIR)/bin
+BPFOBJ := $(BPFOBJ_DIR)/libbpf.a
+ifneq ($(CROSS_COMPILE),)
+HOST_BUILD_DIR := $(OBJ_DIR)/host
+HOST_OUTPUT_DIR := host-tools
+HOST_INCLUDE_DIR := $(HOST_OUTPUT_DIR)/include
+else
+HOST_BUILD_DIR := $(OBJ_DIR)
+HOST_OUTPUT_DIR := $(OUTPUT_DIR)
+HOST_INCLUDE_DIR := $(INCLUDE_DIR)
+endif
+HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
+RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
+DEFAULT_BPFTOOL := $(HOST_OUTPUT_DIR)/sbin/bpftool
+
+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$(CURDIR)/include
+
+# Silence some warnings when compiled with clang
+ifneq ($(LLVM),)
+CFLAGS += -Wno-unused-command-line-argument
+endif
+
+LDFLAGS = -lelf -lz -lpthread
+
+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) -v -E - </dev/null 2>&1 \
+ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+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../../include \
+ $(call get_sys_includes,$(CLANG)) \
+ -Wall -Wno-compare-distinct-pointer-types \
+ -O2 -mcpu=v3
+
+# sort removes libbpf duplicates when not cross-building
+MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \
+ $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids \
+ $(INCLUDE_DIR) $(SCXOBJ_DIR) $(BINDIR))
+
+$(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/ \
+ EXTRA_CFLAGS='-g -O0 -fPIC' \
+ DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
+
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
+ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
+ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \
+ EXTRA_CFLAGS='-g -O0' \
+ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
+ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \
+ LIBBPF_DESTDIR=$(HOST_OUTPUT_DIR)/ \
+ prefix= DESTDIR=$(HOST_OUTPUT_DIR)/ install-bin
+
+$(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 include/scx/*.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)
+ $(eval sched=$(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)
+
+SCX_COMMON_DEPS := include/scx/common.h include/scx/user_exit_info.h | $(BINDIR)
+
+c-sched-targets = scx_simple scx_qmap scx_central scx_flatcg
+
+$(addprefix $(BINDIR)/,$(c-sched-targets)): \
+ $(BINDIR)/%: \
+ $(filter-out %.bpf.c,%.c) \
+ $(INCLUDE_DIR)/%.bpf.skel.h \
+ $(SCX_COMMON_DEPS)
+ $(eval sched=$(notdir $@))
+ $(CC) $(CFLAGS) -c $(sched).c -o $(SCXOBJ_DIR)/$(sched).o
+ $(CC) -o $@ $(SCXOBJ_DIR)/$(sched).o $(HOST_BPFOBJ) $(LDFLAGS)
+
+$(c-sched-targets): %: $(BINDIR)/%
+
+install: all
+ $(Q)mkdir -p $(DESTDIR)/usr/local/bin/
+ $(Q)cp $(BINDIR)/* $(DESTDIR)/usr/local/bin/
+
+clean:
+ rm -rf $(OUTPUT_DIR) $(HOST_OUTPUT_DIR)
+ rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h
+ rm -f $(c-sched-targets)
+
+help:
+ @echo 'Building targets'
+ @echo '================'
+ @echo ''
+ @echo ' all - Compile all schedulers'
+ @echo ''
+ @echo 'Alternatively, you may compile individual schedulers:'
+ @echo ''
+ @printf ' %s\n' $(c-sched-targets)
+ @echo ''
+ @echo 'For any scheduler build target, you may specify an alternative'
+ @echo 'build output path with the O= environment variable. For example:'
+ @echo ''
+ @echo ' O=/tmp/sched_ext make all'
+ @echo ''
+ @echo 'will compile all schedulers, and emit the build artifacts to'
+ @echo '/tmp/sched_ext/build.'
+ @echo ''
+ @echo ''
+ @echo 'Installing targets'
+ @echo '=================='
+ @echo ''
+ @echo ' install - Compile and install all schedulers to /usr/bin.'
+ @echo ' You may specify the DESTDIR= environment variable'
+ @echo ' to indicate a prefix for /usr/bin. For example:'
+ @echo ''
+ @echo ' DESTDIR=/tmp/sched_ext make install'
+ @echo ''
+ @echo ' will build the schedulers in CWD/build, and'
+ @echo ' install the schedulers to /tmp/sched_ext/usr/bin.'
+ @echo ''
+ @echo ''
+ @echo 'Cleaning targets'
+ @echo '================'
+ @echo ''
+ @echo ' clean - Remove all generated files'
+
+all_targets: $(c-sched-targets)
+
+.PHONY: all all_targets $(c-sched-targets) clean help
+
+# delete failed targets
+.DELETE_ON_ERROR:
+
+# keep intermediate (.bpf.skel.h, .bpf.o, etc) targets
+.SECONDARY:
diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md
new file mode 100644
index 000000000000..16a42e4060f6
--- /dev/null
+++ b/tools/sched_ext/README.md
@@ -0,0 +1,270 @@
+SCHED_EXT EXAMPLE SCHEDULERS
+============================
+
+# Introduction
+
+This directory contains a number of example sched_ext schedulers. These
+schedulers are meant to provide examples of different types of schedulers
+that can be built using sched_ext, and illustrate how various features of
+sched_ext can be used.
+
+Some of the examples are performant, production-ready schedulers. That is, for
+the correct workload and with the correct tuning, they may be deployed in a
+production environment with acceptable or possibly even improved performance.
+Others are just examples that in practice, would not provide acceptable
+performance (though they could be improved to get there).
+
+This README will describe these example schedulers, including describing the
+types of workloads or scenarios they're designed to accommodate, and whether or
+not they're production ready. For more details on any of these schedulers,
+please see the header comment in their .bpf.c file.
+
+
+# Compiling the examples
+
+There are a few toolchain dependencies for compiling the example schedulers.
+
+## Toolchain dependencies
+
+1. clang >= 16.0.0
+
+The schedulers are BPF programs, and therefore must be compiled with clang. gcc
+is actively working on adding a BPF backend compiler as well, but are still
+missing some features such as BTF type tags which are necessary for using
+kptrs.
+
+2. pahole >= 1.25
+
+You may need pahole in order to generate BTF from DWARF.
+
+3. rust >= 1.70.0
+
+Rust schedulers uses features present in the rust toolchain >= 1.70.0. You
+should be able to use the stable build from rustup, but if that doesn't
+work, try using the rustup nightly build.
+
+There are other requirements as well, such as make, but these are the main /
+non-trivial ones.
+
+## Compiling the kernel
+
+In order to run a sched_ext scheduler, you'll have to run a kernel compiled
+with the patches in this repository, and with a minimum set of necessary
+Kconfig options:
+
+```
+CONFIG_BPF=y
+CONFIG_SCHED_CLASS_EXT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_DEBUG_INFO_BTF=y
+```
+
+It's also recommended that you also include the following Kconfig options:
+
+```
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_JIT_DEFAULT_ON=y
+CONFIG_PAHOLE_HAS_SPLIT_BTF=y
+CONFIG_PAHOLE_HAS_BTF_TAG=y
+```
+
+There is a `Kconfig` file in this directory whose contents you can append to
+your local `.config` file, as long as there are no conflicts with any existing
+options in the file.
+
+## Getting a vmlinux.h file
+
+You may notice that most of the example schedulers include a "vmlinux.h" file.
+This is a large, auto-generated header file that contains all of the types
+defined in some vmlinux binary that was compiled with
+[BTF](https://docs.kernel.org/bpf/btf.html) (i.e. with the BTF-related Kconfig
+options specified above).
+
+The header file is created using `bpftool`, by passing it a vmlinux binary
+compiled with BTF as follows:
+
+```bash
+$ bpftool btf dump file /path/to/vmlinux format c > vmlinux.h
+```
+
+`bpftool` analyzes all of the BTF encodings in the binary, and produces a
+header file that can be included by BPF programs to access those types. For
+example, using vmlinux.h allows a scheduler to access fields defined directly
+in vmlinux as follows:
+
+```c
+#include "vmlinux.h"
+// vmlinux.h is also implicitly included by scx_common.bpf.h.
+#include "scx_common.bpf.h"
+
+/*
+ * vmlinux.h provides definitions for struct task_struct and
+ * struct scx_enable_args.
+ */
+void BPF_STRUCT_OPS(example_enable, struct task_struct *p,
+ struct scx_enable_args *args)
+{
+ bpf_printk("Task %s enabled in example scheduler", p->comm);
+}
+
+// vmlinux.h provides the definition for struct sched_ext_ops.
+SEC(".struct_ops.link")
+struct sched_ext_ops example_ops {
+ .enable = (void *)example_enable,
+ .name = "example",
+}
+```
+
+The scheduler build system will generate this vmlinux.h file as part of the
+scheduler build pipeline. It looks for a vmlinux file in the following
+dependency order:
+
+1. If the O= environment variable is defined, at `$O/vmlinux`
+2. If the KBUILD_OUTPUT= environment variable is defined, at
+ `$KBUILD_OUTPUT/vmlinux`
+3. At `../../vmlinux` (i.e. at the root of the kernel tree where you're
+ compiling the schedulers)
+3. `/sys/kernel/btf/vmlinux`
+4. `/boot/vmlinux-$(uname -r)`
+
+In other words, if you have compiled a kernel in your local repo, its vmlinux
+file will be used to generate vmlinux.h. Otherwise, it will be the vmlinux of
+the kernel you're currently running on. This means that if you're running on a
+kernel with sched_ext support, you may not need to compile a local kernel at
+all.
+
+### Aside on CO-RE
+
+One of the cooler features of BPF is that it supports
+[CO-RE](https://nakryiko.com/posts/bpf-core-reference-guide/) (Compile Once Run
+Everywhere). This feature allows you to reference fields inside of structs with
+types defined internal to the kernel, and not have to recompile if you load the
+BPF program on a different kernel with the field at a different offset. In our
+example above, we print out a task name with `p->comm`. CO-RE would perform
+relocations for that access when the program is loaded to ensure that it's
+referencing the correct offset for the currently running kernel.
+
+## Compiling the schedulers
+
+Once you have your toolchain setup, and a vmlinux that can be used to generate
+a full vmlinux.h file, you can compile the schedulers using `make`:
+
+```bash
+$ make -j($nproc)
+```
+
+# Example schedulers
+
+This directory contains the following example schedulers. These schedulers are
+for testing and demonstrating different aspects of sched_ext. While some may be
+useful in limited scenarios, they are not intended to be practical.
+
+For more scheduler implementations, tools and documentation, visit
+https://github.com/sched-ext/scx.
+
+## scx_simple
+
+A simple scheduler that provides an example of a minimal sched_ext scheduler.
+scx_simple can be run in either global weighted vtime mode, or FIFO mode.
+
+Though very simple, in limited scenarios, this scheduler can perform reasonably
+well on single-socket systems with a unified L3 cache.
+
+## scx_qmap
+
+Another simple, yet slightly more complex scheduler that provides an example of
+a basic weighted FIFO queuing policy. It also provides examples of some common
+useful BPF features, such as sleepable per-task storage allocation in the
+`ops.prep_enable()` callback, and using the `BPF_MAP_TYPE_QUEUE` map type to
+enqueue tasks. It also illustrates how core-sched support could be implemented.
+
+## scx_central
+
+A "central" scheduler where scheduling decisions are made from a single CPU.
+This scheduler illustrates how scheduling decisions can be dispatched from a
+single CPU, allowing other cores to run with infinite slices, without timer
+ticks, and without having to incur the overhead of making scheduling decisions.
+
+The approach demonstrated by this scheduler may be useful for any workload that
+benefits from minimizing scheduling overhead and timer ticks. An example of
+where this could be particularly useful is running VMs, where running with
+infinite slices and no timer ticks allows the VM to avoid unnecessary expensive
+vmexits.
+
+## scx_flatcg
+
+A flattened cgroup hierarchy scheduler. This scheduler implements hierarchical
+weight-based cgroup CPU control by flattening the cgroup hierarchy into a single
+layer, by compounding the active weight share at each level. The effect of this
+is a much more performant CPU controller, which does not need to descend down
+cgroup trees in order to properly compute a cgroup's share.
+
+Similar to scx_simple, in limited scenarios, this scheduler can perform
+reasonably well on single socket-socket systems with a unified L3 cache and show
+significantly lowered hierarchical scheduling overhead.
+
+
+# Troubleshooting
+
+There are a number of common issues that you may run into when building the
+schedulers. We'll go over some of the common ones here.
+
+## Build Failures
+
+### Old version of clang
+
+```
+error: static assertion failed due to requirement 'SCX_DSQ_FLAG_BUILTIN': bpftool generated vmlinux.h is missing high bits for 64bit enums, upgrade clang and pahole
+ _Static_assert(SCX_DSQ_FLAG_BUILTIN,
+ ^~~~~~~~~~~~~~~~~~~~
+1 error generated.
+```
+
+This means you built the kernel or the schedulers with an older version of
+clang than what's supported (i.e. older than 16.0.0). To remediate this:
+
+1. `which clang` to make sure you're using a sufficiently new version of clang.
+
+2. `make fullclean` in the root path of the repository, and rebuild the kernel
+ and schedulers.
+
+3. Rebuild the kernel, and then your example schedulers.
+
+The schedulers are also cleaned if you invoke `make mrproper` in the root
+directory of the tree.
+
+### Stale kernel build / incomplete vmlinux.h file
+
+As described above, you'll need a `vmlinux.h` file that was generated from a
+vmlinux built with BTF, and with sched_ext support enabled. If you don't,
+you'll see errors such as the following which indicate that a type being
+referenced in a scheduler is unknown:
+
+```
+/path/to/sched_ext/tools/sched_ext/user_exit_info.h:25:23: note: forward declaration of 'struct scx_exit_info'
+
+const struct scx_exit_info *ei)
+
+^
+```
+
+In order to resolve this, please follow the steps above in
+[Getting a vmlinux.h file](#getting-a-vmlinuxh-file) in order to ensure your
+schedulers are using a vmlinux.h file that includes the requisite types.
+
+## Misc
+
+### llvm: [OFF]
+
+You may see the following output when building the schedulers:
+
+```
+Auto-detecting system features:
+... clang-bpf-co-re: [ on ]
+... llvm: [ OFF ]
+... libcap: [ on ]
+... libbfd: [ on ]
+```
+
+Seeing `llvm: [ OFF ]` here is not an issue. You can safely ignore.
diff --git a/tools/sched_ext/include/bpf-compat/gnu/stubs.h b/tools/sched_ext/include/bpf-compat/gnu/stubs.h
new file mode 100644
index 000000000000..ad7d139ce907
--- /dev/null
+++ b/tools/sched_ext/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.
+ */
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
new file mode 100644
index 000000000000..225f61f9bfca
--- /dev/null
+++ b/tools/sched_ext/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 */
diff --git a/tools/sched_ext/include/scx/common.h b/tools/sched_ext/include/scx/common.h
new file mode 100644
index 000000000000..5b0f90152152
--- /dev/null
+++ b/tools/sched_ext/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 */
diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h
new file mode 100644
index 000000000000..e5afe9efd3f3
--- /dev/null
+++ b/tools/sched_ext/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 */
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
new file mode 100644
index 000000000000..cc56ff9aa252
--- /dev/null
+++ b/tools/sched_ext/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 */
diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h
new file mode 100644
index 000000000000..8ce2734402e1
--- /dev/null
+++ b/tools/sched_ext/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 */
diff --git a/tools/sched_ext/scx_central.bpf.c b/tools/sched_ext/scx_central.bpf.c
new file mode 100644
index 000000000000..8dd8eb73b6b8
--- /dev/null
+++ b/tools/sched_ext/scx_central.bpf.c
@@ -0,0 +1,361 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A central FIFO sched_ext scheduler which demonstrates the followings:
+ *
+ * a. Making all scheduling decisions from one CPU:
+ *
+ * The central CPU is the only one making scheduling decisions. All other
+ * CPUs kick the central CPU when they run out of tasks to run.
+ *
+ * There is one global BPF queue and the central CPU schedules all CPUs by
+ * dispatching from the global queue to each CPU's local dsq from dispatch().
+ * This isn't the most straightforward. e.g. It'd be easier to bounce
+ * through per-CPU BPF queues. The current design is chosen to maximally
+ * utilize and verify various SCX mechanisms such as LOCAL_ON dispatching.
+ *
+ * b. Tickless operation
+ *
+ * All tasks are dispatched with the infinite slice which allows stopping the
+ * ticks on CONFIG_NO_HZ_FULL kernels running with the proper nohz_full
+ * parameter. The tickless operation can be observed through
+ * /proc/interrupts.
+ *
+ * Periodic switching is enforced by a periodic timer checking all CPUs and
+ * preempting them as necessary. Unfortunately, BPF timer currently doesn't
+ * have a way to pin to a specific CPU, so the periodic timer isn't pinned to
+ * the central CPU.
+ *
+ * c. Preemption
+ *
+ * Kthreads are unconditionally queued to the head of a matching local dsq
+ * and dispatched with SCX_DSQ_PREEMPT. This ensures that a kthread is always
+ * prioritized over user threads, which is required for ensuring forward
+ * progress as e.g. the periodic timer may run on a ksoftirqd and if the
+ * ksoftirqd gets starved by a user thread, there may not be anything else to
+ * vacate that user thread.
+ *
+ * SCX_KICK_PREEMPT is used to trigger scheduling and CPUs to move to the
+ * next tasks.
+ *
+ * This scheduler is designed to maximize usage of various SCX mechanisms. A
+ * more practical implementation would likely put the scheduling loop outside
+ * the central CPU's dispatch() path and add some form of priority mechanism.
+ *
+ * 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";
+
+enum {
+ FALLBACK_DSQ_ID = 0,
+ MS_TO_NS = 1000LLU * 1000,
+ TIMER_INTERVAL_NS = 1 * MS_TO_NS,
+};
+
+const volatile s32 central_cpu;
+const volatile u32 nr_cpu_ids = 1; /* !0 for veristat, set during init */
+const volatile u64 slice_ns = SCX_SLICE_DFL;
+
+bool timer_pinned = true;
+u64 nr_total, nr_locals, nr_queued, nr_lost_pids;
+u64 nr_timers, nr_dispatches, nr_mismatches, nr_retries;
+u64 nr_overflows;
+
+UEI_DEFINE(uei);
+
+struct {
+ __uint(type, BPF_MAP_TYPE_QUEUE);
+ __uint(max_entries, 4096);
+ __type(value, s32);
+} central_q SEC(".maps");
+
+/* can't use percpu map due to bad lookups */
+bool RESIZABLE_ARRAY(data, cpu_gimme_task);
+u64 RESIZABLE_ARRAY(data, cpu_started_at);
+
+struct central_timer {
+ struct bpf_timer timer;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, u32);
+ __type(value, struct central_timer);
+} central_timer SEC(".maps");
+
+static bool vtime_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+s32 BPF_STRUCT_OPS(central_select_cpu, struct task_struct *p,
+ s32 prev_cpu, u64 wake_flags)
+{
+ /*
+ * Steer wakeups to the central CPU as much as possible to avoid
+ * disturbing other CPUs. It's safe to blindly return the central cpu as
+ * select_cpu() is a hint and if @p can't be on it, the kernel will
+ * automatically pick a fallback CPU.
+ */
+ return central_cpu;
+}
+
+void BPF_STRUCT_OPS(central_enqueue, struct task_struct *p, u64 enq_flags)
+{
+ s32 pid = p->pid;
+
+ __sync_fetch_and_add(&nr_total, 1);
+
+ /*
+ * Push per-cpu kthreads at the head of local dsq's and preempt the
+ * corresponding CPU. This ensures that e.g. ksoftirqd isn't blocked
+ * behind other threads which is necessary for forward progress
+ * guarantee as we depend on the BPF timer which may run from ksoftirqd.
+ */
+ if ((p->flags & PF_KTHREAD) && p->nr_cpus_allowed == 1) {
+ __sync_fetch_and_add(&nr_locals, 1);
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+ enq_flags | SCX_ENQ_PREEMPT);
+ return;
+ }
+
+ if (bpf_map_push_elem(&central_q, &pid, 0)) {
+ __sync_fetch_and_add(&nr_overflows, 1);
+ scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, enq_flags);
+ return;
+ }
+
+ __sync_fetch_and_add(&nr_queued, 1);
+
+ if (!scx_bpf_task_running(p))
+ scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+}
+
+static bool dispatch_to_cpu(s32 cpu)
+{
+ struct task_struct *p;
+ s32 pid;
+
+ bpf_repeat(BPF_MAX_LOOPS) {
+ if (bpf_map_pop_elem(&central_q, &pid))
+ break;
+
+ __sync_fetch_and_sub(&nr_queued, 1);
+
+ p = bpf_task_from_pid(pid);
+ if (!p) {
+ __sync_fetch_and_add(&nr_lost_pids, 1);
+ continue;
+ }
+
+ /*
+ * If we can't run the task at the top, do the dumb thing and
+ * bounce it to the fallback dsq.
+ */
+ if (!bpf_cpumask_test_cpu(cpu, p->cpus_ptr)) {
+ __sync_fetch_and_add(&nr_mismatches, 1);
+ scx_bpf_dispatch(p, FALLBACK_DSQ_ID, SCX_SLICE_INF, 0);
+ bpf_task_release(p);
+ /*
+ * We might run out of dispatch buffer slots if we continue dispatching
+ * to the fallback DSQ, without dispatching to the local DSQ of the
+ * target CPU. In such a case, break the loop now as will fail the
+ * next dispatch operation.
+ */
+ if (!scx_bpf_dispatch_nr_slots())
+ break;
+ continue;
+ }
+
+ /* dispatch to local and mark that @cpu doesn't need more */
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, SCX_SLICE_INF, 0);
+
+ if (cpu != central_cpu)
+ scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+
+ bpf_task_release(p);
+ return true;
+ }
+
+ return false;
+}
+
+void BPF_STRUCT_OPS(central_dispatch, s32 cpu, struct task_struct *prev)
+{
+ if (cpu == central_cpu) {
+ /* dispatch for all other CPUs first */
+ __sync_fetch_and_add(&nr_dispatches, 1);
+
+ bpf_for(cpu, 0, nr_cpu_ids) {
+ bool *gimme;
+
+ if (!scx_bpf_dispatch_nr_slots())
+ break;
+
+ /* central's gimme is never set */
+ gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids);
+ if (!gimme || !*gimme)
+ continue;
+
+ if (dispatch_to_cpu(cpu))
+ *gimme = false;
+ }
+
+ /*
+ * Retry if we ran out of dispatch buffer slots as we might have
+ * skipped some CPUs and also need to dispatch for self. The ext
+ * core automatically retries if the local dsq is empty but we
+ * can't rely on that as we're dispatching for other CPUs too.
+ * Kick self explicitly to retry.
+ */
+ if (!scx_bpf_dispatch_nr_slots()) {
+ __sync_fetch_and_add(&nr_retries, 1);
+ scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+ return;
+ }
+
+ /* look for a task to run on the central CPU */
+ if (scx_bpf_consume(FALLBACK_DSQ_ID))
+ return;
+ dispatch_to_cpu(central_cpu);
+ } else {
+ bool *gimme;
+
+ if (scx_bpf_consume(FALLBACK_DSQ_ID))
+ return;
+
+ gimme = ARRAY_ELEM_PTR(cpu_gimme_task, cpu, nr_cpu_ids);
+ if (gimme)
+ *gimme = true;
+
+ /*
+ * Force dispatch on the scheduling CPU so that it finds a task
+ * to run for us.
+ */
+ scx_bpf_kick_cpu(central_cpu, SCX_KICK_PREEMPT);
+ }
+}
+
+void BPF_STRUCT_OPS(central_running, struct task_struct *p)
+{
+ s32 cpu = scx_bpf_task_cpu(p);
+ u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+ if (started_at)
+ *started_at = bpf_ktime_get_ns() ?: 1; /* 0 indicates idle */
+}
+
+void BPF_STRUCT_OPS(central_stopping, struct task_struct *p, bool runnable)
+{
+ s32 cpu = scx_bpf_task_cpu(p);
+ u64 *started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+ if (started_at)
+ *started_at = 0;
+}
+
+static int central_timerfn(void *map, int *key, struct bpf_timer *timer)
+{
+ u64 now = bpf_ktime_get_ns();
+ u64 nr_to_kick = nr_queued;
+ s32 i, curr_cpu;
+
+ curr_cpu = bpf_get_smp_processor_id();
+ if (timer_pinned && (curr_cpu != central_cpu)) {
+ scx_bpf_error("Central timer ran on CPU %d, not central CPU %d",
+ curr_cpu, central_cpu);
+ return 0;
+ }
+
+ bpf_for(i, 0, nr_cpu_ids) {
+ s32 cpu = (nr_timers + i) % nr_cpu_ids;
+ u64 *started_at;
+
+ if (cpu == central_cpu)
+ continue;
+
+ /* kick iff the current one exhausted its slice */
+ started_at = ARRAY_ELEM_PTR(cpu_started_at, cpu, nr_cpu_ids);
+ if (started_at && *started_at &&
+ vtime_before(now, *started_at + slice_ns))
+ continue;
+
+ /* and there's something pending */
+ if (scx_bpf_dsq_nr_queued(FALLBACK_DSQ_ID) ||
+ scx_bpf_dsq_nr_queued(SCX_DSQ_LOCAL_ON | cpu))
+ ;
+ else if (nr_to_kick)
+ nr_to_kick--;
+ else
+ continue;
+
+ scx_bpf_kick_cpu(cpu, SCX_KICK_PREEMPT);
+ }
+
+ bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN);
+ __sync_fetch_and_add(&nr_timers, 1);
+ return 0;
+}
+
+int BPF_STRUCT_OPS_SLEEPABLE(central_init)
+{
+ u32 key = 0;
+ struct bpf_timer *timer;
+ int ret;
+
+ ret = scx_bpf_create_dsq(FALLBACK_DSQ_ID, -1);
+ if (ret)
+ return ret;
+
+ timer = bpf_map_lookup_elem(&central_timer, &key);
+ if (!timer)
+ return -ESRCH;
+
+ if (bpf_get_smp_processor_id() != central_cpu) {
+ scx_bpf_error("init from non-central CPU");
+ return -EINVAL;
+ }
+
+ bpf_timer_init(timer, &central_timer, CLOCK_MONOTONIC);
+ bpf_timer_set_callback(timer, central_timerfn);
+
+ ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, BPF_F_TIMER_CPU_PIN);
+ /*
+ * BPF_F_TIMER_CPU_PIN is pretty new (>=6.7). If we're running in a
+ * kernel which doesn't have it, bpf_timer_start() will return -EINVAL.
+ * Retry without the PIN. This would be the perfect use case for
+ * bpf_core_enum_value_exists() but the enum type doesn't have a name
+ * and can't be used with bpf_core_enum_value_exists(). Oh well...
+ */
+ if (ret == -EINVAL) {
+ timer_pinned = false;
+ ret = bpf_timer_start(timer, TIMER_INTERVAL_NS, 0);
+ }
+ if (ret)
+ scx_bpf_error("bpf_timer_start failed (%d)", ret);
+ return ret;
+}
+
+void BPF_STRUCT_OPS(central_exit, struct scx_exit_info *ei)
+{
+ UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(central_ops,
+ /*
+ * We are offloading all scheduling decisions to the central CPU
+ * and thus being the last task on a given CPU doesn't mean
+ * anything special. Enqueue the last tasks like any other tasks.
+ */
+ .flags = SCX_OPS_ENQ_LAST,
+
+ .select_cpu = (void *)central_select_cpu,
+ .enqueue = (void *)central_enqueue,
+ .dispatch = (void *)central_dispatch,
+ .running = (void *)central_running,
+ .stopping = (void *)central_stopping,
+ .init = (void *)central_init,
+ .exit = (void *)central_exit,
+ .name = "central");
diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
new file mode 100644
index 000000000000..21deea320bd7
--- /dev/null
+++ b/tools/sched_ext/scx_central.c
@@ -0,0 +1,135 @@
+/* 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>
+ */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_central.bpf.skel.h"
+
+const char help_fmt[] =
+"A central FIFO sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-s SLICE_US] [-c CPU]\n"
+"\n"
+" -s SLICE_US Override slice duration\n"
+" -c CPU Override the central CPU (default: 0)\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 dummy)
+{
+ exit_req = 1;
+}
+
+int main(int argc, char **argv)
+{
+ struct scx_central *skel;
+ struct bpf_link *link;
+ __u64 seq = 0, ecode;
+ __s32 opt;
+ cpu_set_t *cpuset;
+
+ libbpf_set_print(libbpf_print_fn);
+ signal(SIGINT, sigint_handler);
+ signal(SIGTERM, sigint_handler);
+restart:
+ skel = SCX_OPS_OPEN(central_ops, scx_central);
+
+ skel->rodata->central_cpu = 0;
+ skel->rodata->nr_cpu_ids = libbpf_num_possible_cpus();
+
+ while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) {
+ switch (opt) {
+ case 's':
+ skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
+ break;
+ case 'c':
+ skel->rodata->central_cpu = strtoul(optarg, NULL, 0);
+ break;
+ case 'v':
+ verbose = true;
+ break;
+ default:
+ fprintf(stderr, help_fmt, basename(argv[0]));
+ return opt != 'h';
+ }
+ }
+
+ /* Resize arrays so their element count is equal to cpu count. */
+ RESIZE_ARRAY(skel, data, cpu_gimme_task, skel->rodata->nr_cpu_ids);
+ RESIZE_ARRAY(skel, data, cpu_started_at, skel->rodata->nr_cpu_ids);
+
+ SCX_OPS_LOAD(skel, central_ops, scx_central, uei);
+
+ /*
+ * Affinitize the loading thread to the central CPU, as:
+ * - That's where the BPF timer is first invoked in the BPF program.
+ * - We probably don't want this user space component to take up a core
+ * from a task that would benefit from avoiding preemption on one of
+ * the tickless cores.
+ *
+ * Until BPF supports pinning the timer, it's not guaranteed that it
+ * will always be invoked on the central CPU. In practice, this
+ * suffices the majority of the time.
+ */
+ cpuset = CPU_ALLOC(skel->rodata->nr_cpu_ids);
+ SCX_BUG_ON(!cpuset, "Failed to allocate cpuset");
+ CPU_ZERO(cpuset);
+ CPU_SET(skel->rodata->central_cpu, cpuset);
+ SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset),
+ "Failed to affinitize to central CPU %d (max %d)",
+ skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1);
+ CPU_FREE(cpuset);
+
+ link = SCX_OPS_ATTACH(skel, central_ops, scx_central);
+
+ if (!skel->data->timer_pinned)
+ printf("WARNING : BPF_F_TIMER_CPU_PIN not available, timer not pinned to central\n");
+
+ while (!exit_req && !UEI_EXITED(skel, uei)) {
+ printf("[SEQ %llu]\n", seq++);
+ printf("total :%10" PRIu64 " local:%10" PRIu64 " queued:%10" PRIu64 " lost:%10" PRIu64 "\n",
+ skel->bss->nr_total,
+ skel->bss->nr_locals,
+ skel->bss->nr_queued,
+ skel->bss->nr_lost_pids);
+ printf("timer :%10" PRIu64 " dispatch:%10" PRIu64 " mismatch:%10" PRIu64 " retry:%10" PRIu64 "\n",
+ skel->bss->nr_timers,
+ skel->bss->nr_dispatches,
+ skel->bss->nr_mismatches,
+ skel->bss->nr_retries);
+ printf("overflow:%10" PRIu64 "\n",
+ skel->bss->nr_overflows);
+ fflush(stdout);
+ sleep(1);
+ }
+
+ bpf_link__destroy(link);
+ ecode = UEI_REPORT(skel, uei);
+ scx_central__destroy(skel);
+
+ if (UEI_ECODE_RESTART(ecode))
+ goto restart;
+ return 0;
+}
diff --git a/tools/sched_ext/scx_flatcg.bpf.c b/tools/sched_ext/scx_flatcg.bpf.c
new file mode 100644
index 000000000000..b722baf6da4b
--- /dev/null
+++ b/tools/sched_ext/scx_flatcg.bpf.c
@@ -0,0 +1,957 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A demo sched_ext flattened cgroup hierarchy scheduler. It implements
+ * hierarchical weight-based cgroup CPU control by flattening the cgroup
+ * hierarchy into a single layer by compounding the active weight share at each
+ * level. Consider the following hierarchy with weights in parentheses:
+ *
+ * R + A (100) + B (100)
+ * | \ C (100)
+ * \ D (200)
+ *
+ * Ignoring the root and threaded cgroups, only B, C and D can contain tasks.
+ * Let's say all three have runnable tasks. The total share that each of these
+ * three cgroups is entitled to can be calculated by compounding its share at
+ * each level.
+ *
+ * For example, B is competing against C and in that competition its share is
+ * 100/(100+100) == 1/2. At its parent level, A is competing against D and A's
+ * share in that competition is 100/(200+100) == 1/3. B's eventual share in the
+ * system can be calculated by multiplying the two shares, 1/2 * 1/3 == 1/6. C's
+ * eventual shaer is the same at 1/6. D is only competing at the top level and
+ * its share is 200/(100+200) == 2/3.
+ *
+ * So, instead of hierarchically scheduling level-by-level, we can consider it
+ * as B, C and D competing each other with respective share of 1/6, 1/6 and 2/3
+ * and keep updating the eventual shares as the cgroups' runnable states change.
+ *
+ * This flattening of hierarchy can bring a substantial performance gain when
+ * the cgroup hierarchy is nested multiple levels. in a simple benchmark using
+ * wrk[8] on apache serving a CGI script calculating sha1sum of a small file, it
+ * outperforms CFS by ~3% with CPU controller disabled and by ~10% with two
+ * apache instances competing with 2:1 weight ratio nested four level deep.
+ *
+ * However, the gain comes at the cost of not being able to properly handle
+ * thundering herd of cgroups. For example, if many cgroups which are nested
+ * behind a low priority parent cgroup wake up around the same time, they may be
+ * able to consume more CPU cycles than they are entitled to. In many use cases,
+ * this isn't a real concern especially given the performance gain. Also, there
+ * are ways to mitigate the problem further by e.g. introducing an extra
+ * scheduling layer on cgroup delegation boundaries.
+ *
+ * The scheduler first picks the cgroup to run and then schedule the tasks
+ * within by using nested weighted vtime scheduling by default. The
+ * cgroup-internal scheduling can be switched to FIFO with the -f option.
+ */
+#include <scx/common.bpf.h>
+#include "scx_flatcg.h"
+
+/*
+ * Maximum amount of retries to find a valid cgroup.
+ */
+enum {
+ FALLBACK_DSQ = 0,
+ CGROUP_MAX_RETRIES = 1024,
+};
+
+char _license[] SEC("license") = "GPL";
+
+const volatile u32 nr_cpus = 32; /* !0 for veristat, set during init */
+const volatile u64 cgrp_slice_ns = SCX_SLICE_DFL;
+const volatile bool fifo_sched;
+
+u64 cvtime_now;
+UEI_DEFINE(uei);
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __type(key, u32);
+ __type(value, u64);
+ __uint(max_entries, FCG_NR_STATS);
+} stats SEC(".maps");
+
+static void stat_inc(enum fcg_stat_idx idx)
+{
+ u32 idx_v = idx;
+
+ u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx_v);
+ if (cnt_p)
+ (*cnt_p)++;
+}
+
+struct fcg_cpu_ctx {
+ u64 cur_cgid;
+ u64 cur_at;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __type(key, u32);
+ __type(value, struct fcg_cpu_ctx);
+ __uint(max_entries, 1);
+} cpu_ctx SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CGRP_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct fcg_cgrp_ctx);
+} cgrp_ctx SEC(".maps");
+
+struct cgv_node {
+ struct bpf_rb_node rb_node;
+ __u64 cvtime;
+ __u64 cgid;
+};
+
+private(CGV_TREE) struct bpf_spin_lock cgv_tree_lock;
+private(CGV_TREE) struct bpf_rb_root cgv_tree __contains(cgv_node, rb_node);
+
+struct cgv_node_stash {
+ struct cgv_node __kptr *node;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 16384);
+ __type(key, __u64);
+ __type(value, struct cgv_node_stash);
+} cgv_node_stash SEC(".maps");
+
+struct fcg_task_ctx {
+ u64 bypassed_at;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct fcg_task_ctx);
+} task_ctx SEC(".maps");
+
+/* gets inc'd on weight tree changes to expire the cached hweights */
+u64 hweight_gen = 1;
+
+static u64 div_round_up(u64 dividend, u64 divisor)
+{
+ return (dividend + divisor - 1) / divisor;
+}
+
+static bool vtime_before(u64 a, u64 b)
+{
+ return (s64)(a - b) < 0;
+}
+
+static bool cgv_node_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+ struct cgv_node *cgc_a, *cgc_b;
+
+ cgc_a = container_of(a, struct cgv_node, rb_node);
+ cgc_b = container_of(b, struct cgv_node, rb_node);
+
+ return cgc_a->cvtime < cgc_b->cvtime;
+}
+
+static struct fcg_cpu_ctx *find_cpu_ctx(void)
+{
+ struct fcg_cpu_ctx *cpuc;
+ u32 idx = 0;
+
+ cpuc = bpf_map_lookup_elem(&cpu_ctx, &idx);
+ if (!cpuc) {
+ scx_bpf_error("cpu_ctx lookup failed");
+ return NULL;
+ }
+ return cpuc;
+}
+
+static struct fcg_cgrp_ctx *find_cgrp_ctx(struct cgroup *cgrp)
+{
+ struct fcg_cgrp_ctx *cgc;
+
+ cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0);
+ if (!cgc) {
+ scx_bpf_error("cgrp_ctx lookup failed for cgid %llu", cgrp->kn->id);
+ return NULL;
+ }
+ return cgc;
+}
+
+static struct fcg_cgrp_ctx *find_ancestor_cgrp_ctx(struct cgroup *cgrp, int level)
+{
+ struct fcg_cgrp_ctx *cgc;
+
+ cgrp = bpf_cgroup_ancestor(cgrp, level);
+ if (!cgrp) {
+ scx_bpf_error("ancestor cgroup lookup failed");
+ return NULL;
+ }
+
+ cgc = find_cgrp_ctx(cgrp);
+ if (!cgc)
+ scx_bpf_error("ancestor cgrp_ctx lookup failed");
+ bpf_cgroup_release(cgrp);
+ return cgc;
+}
+
+static void cgrp_refresh_hweight(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc)
+{
+ int level;
+
+ if (!cgc->nr_active) {
+ stat_inc(FCG_STAT_HWT_SKIP);
+ return;
+ }
+
+ if (cgc->hweight_gen == hweight_gen) {
+ stat_inc(FCG_STAT_HWT_CACHE);
+ return;
+ }
+
+ stat_inc(FCG_STAT_HWT_UPDATES);
+ bpf_for(level, 0, cgrp->level + 1) {
+ struct fcg_cgrp_ctx *cgc;
+ bool is_active;
+
+ cgc = find_ancestor_cgrp_ctx(cgrp, level);
+ if (!cgc)
+ break;
+
+ if (!level) {
+ cgc->hweight = FCG_HWEIGHT_ONE;
+ cgc->hweight_gen = hweight_gen;
+ } else {
+ struct fcg_cgrp_ctx *pcgc;
+
+ pcgc = find_ancestor_cgrp_ctx(cgrp, level - 1);
+ if (!pcgc)
+ break;
+
+ /*
+ * We can be opportunistic here and not grab the
+ * cgv_tree_lock and deal with the occasional races.
+ * However, hweight updates are already cached and
+ * relatively low-frequency. Let's just do the
+ * straightforward thing.
+ */
+ bpf_spin_lock(&cgv_tree_lock);
+ is_active = cgc->nr_active;
+ if (is_active) {
+ cgc->hweight_gen = pcgc->hweight_gen;
+ cgc->hweight =
+ div_round_up(pcgc->hweight * cgc->weight,
+ pcgc->child_weight_sum);
+ }
+ bpf_spin_unlock(&cgv_tree_lock);
+
+ if (!is_active) {
+ stat_inc(FCG_STAT_HWT_RACE);
+ break;
+ }
+ }
+ }
+}
+
+static void cgrp_cap_budget(struct cgv_node *cgv_node, struct fcg_cgrp_ctx *cgc)
+{
+ u64 delta, cvtime, max_budget;
+
+ /*
+ * A node which is on the rbtree can't be pointed to from elsewhere yet
+ * and thus can't be updated and repositioned. Instead, we collect the
+ * vtime deltas separately and apply it asynchronously here.
+ */
+ delta = __sync_fetch_and_sub(&cgc->cvtime_delta, cgc->cvtime_delta);
+ cvtime = cgv_node->cvtime + delta;
+
+ /*
+ * Allow a cgroup to carry the maximum budget proportional to its
+ * hweight such that a full-hweight cgroup can immediately take up half
+ * of the CPUs at the most while staying at the front of the rbtree.
+ */
+ max_budget = (cgrp_slice_ns * nr_cpus * cgc->hweight) /
+ (2 * FCG_HWEIGHT_ONE);
+ if (vtime_before(cvtime, cvtime_now - max_budget))
+ cvtime = cvtime_now - max_budget;
+
+ cgv_node->cvtime = cvtime;
+}
+
+static void cgrp_enqueued(struct cgroup *cgrp, struct fcg_cgrp_ctx *cgc)
+{
+ struct cgv_node_stash *stash;
+ struct cgv_node *cgv_node;
+ u64 cgid = cgrp->kn->id;
+
+ /* paired with cmpxchg in try_pick_next_cgroup() */
+ if (__sync_val_compare_and_swap(&cgc->queued, 0, 1)) {
+ stat_inc(FCG_STAT_ENQ_SKIP);
+ return;
+ }
+
+ stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid);
+ if (!stash) {
+ scx_bpf_error("cgv_node lookup failed for cgid %llu", cgid);
+ return;
+ }
+
+ /* NULL if the node is already on the rbtree */
+ cgv_node = bpf_kptr_xchg(&stash->node, NULL);
+ if (!cgv_node) {
+ stat_inc(FCG_STAT_ENQ_RACE);
+ return;
+ }
+
+ bpf_spin_lock(&cgv_tree_lock);
+ cgrp_cap_budget(cgv_node, cgc);
+ bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less);
+ bpf_spin_unlock(&cgv_tree_lock);
+}
+
+static void set_bypassed_at(struct task_struct *p, struct fcg_task_ctx *taskc)
+{
+ /*
+ * Tell fcg_stopping() that this bypassed the regular scheduling path
+ * and should be force charged to the cgroup. 0 is used to indicate that
+ * the task isn't bypassing, so if the current runtime is 0, go back by
+ * one nanosecond.
+ */
+ taskc->bypassed_at = p->se.sum_exec_runtime ?: (u64)-1;
+}
+
+s32 BPF_STRUCT_OPS(fcg_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+ struct fcg_task_ctx *taskc;
+ bool is_idle = false;
+ s32 cpu;
+
+ cpu = scx_bpf_select_cpu_dfl(p, prev_cpu, wake_flags, &is_idle);
+
+ taskc = bpf_task_storage_get(&task_ctx, p, 0, 0);
+ if (!taskc) {
+ scx_bpf_error("task_ctx lookup failed");
+ return cpu;
+ }
+
+ /*
+ * If select_cpu_dfl() is recommending local enqueue, the target CPU is
+ * idle. Follow it and charge the cgroup later in fcg_stopping() after
+ * the fact.
+ */
+ if (is_idle) {
+ set_bypassed_at(p, taskc);
+ stat_inc(FCG_STAT_LOCAL);
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+ }
+
+ return cpu;
+}
+
+void BPF_STRUCT_OPS(fcg_enqueue, struct task_struct *p, u64 enq_flags)
+{
+ struct fcg_task_ctx *taskc;
+ struct cgroup *cgrp;
+ struct fcg_cgrp_ctx *cgc;
+
+ taskc = bpf_task_storage_get(&task_ctx, p, 0, 0);
+ if (!taskc) {
+ scx_bpf_error("task_ctx lookup failed");
+ return;
+ }
+
+ /*
+ * Use the direct dispatching and force charging to deal with tasks with
+ * custom affinities so that we don't have to worry about per-cgroup
+ * dq's containing tasks that can't be executed from some CPUs.
+ */
+ if (p->nr_cpus_allowed != nr_cpus) {
+ set_bypassed_at(p, taskc);
+
+ /*
+ * The global dq is deprioritized as we don't want to let tasks
+ * to boost themselves by constraining its cpumask. The
+ * deprioritization is rather severe, so let's not apply that to
+ * per-cpu kernel threads. This is ham-fisted. We probably wanna
+ * implement per-cgroup fallback dq's instead so that we have
+ * more control over when tasks with custom cpumask get issued.
+ */
+ if (p->nr_cpus_allowed == 1 && (p->flags & PF_KTHREAD)) {
+ stat_inc(FCG_STAT_LOCAL);
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, enq_flags);
+ } else {
+ stat_inc(FCG_STAT_GLOBAL);
+ scx_bpf_dispatch(p, FALLBACK_DSQ, SCX_SLICE_DFL, enq_flags);
+ }
+ return;
+ }
+
+ cgrp = __COMPAT_scx_bpf_task_cgroup(p);
+ cgc = find_cgrp_ctx(cgrp);
+ if (!cgc)
+ goto out_release;
+
+ if (fifo_sched) {
+ scx_bpf_dispatch(p, cgrp->kn->id, SCX_SLICE_DFL, enq_flags);
+ } else {
+ u64 tvtime = p->scx.dsq_vtime;
+
+ /*
+ * Limit the amount of budget that an idling task can accumulate
+ * to one slice.
+ */
+ if (vtime_before(tvtime, cgc->tvtime_now - SCX_SLICE_DFL))
+ tvtime = cgc->tvtime_now - SCX_SLICE_DFL;
+
+ scx_bpf_dispatch_vtime(p, cgrp->kn->id, SCX_SLICE_DFL,
+ tvtime, enq_flags);
+ }
+
+ cgrp_enqueued(cgrp, cgc);
+out_release:
+ bpf_cgroup_release(cgrp);
+}
+
+/*
+ * Walk the cgroup tree to update the active weight sums as tasks wake up and
+ * sleep. The weight sums are used as the base when calculating the proportion a
+ * given cgroup or task is entitled to at each level.
+ */
+static void update_active_weight_sums(struct cgroup *cgrp, bool runnable)
+{
+ struct fcg_cgrp_ctx *cgc;
+ bool updated = false;
+ int idx;
+
+ cgc = find_cgrp_ctx(cgrp);
+ if (!cgc)
+ return;
+
+ /*
+ * In most cases, a hot cgroup would have multiple threads going to
+ * sleep and waking up while the whole cgroup stays active. In leaf
+ * cgroups, ->nr_runnable which is updated with __sync operations gates
+ * ->nr_active updates, so that we don't have to grab the cgv_tree_lock
+ * repeatedly for a busy cgroup which is staying active.
+ */
+ if (runnable) {
+ if (__sync_fetch_and_add(&cgc->nr_runnable, 1))
+ return;
+ stat_inc(FCG_STAT_ACT);
+ } else {
+ if (__sync_sub_and_fetch(&cgc->nr_runnable, 1))
+ return;
+ stat_inc(FCG_STAT_DEACT);
+ }
+
+ /*
+ * If @cgrp is becoming runnable, its hweight should be refreshed after
+ * it's added to the weight tree so that enqueue has the up-to-date
+ * value. If @cgrp is becoming quiescent, the hweight should be
+ * refreshed before it's removed from the weight tree so that the usage
+ * charging which happens afterwards has access to the latest value.
+ */
+ if (!runnable)
+ cgrp_refresh_hweight(cgrp, cgc);
+
+ /* propagate upwards */
+ bpf_for(idx, 0, cgrp->level) {
+ int level = cgrp->level - idx;
+ struct fcg_cgrp_ctx *cgc, *pcgc = NULL;
+ bool propagate = false;
+
+ cgc = find_ancestor_cgrp_ctx(cgrp, level);
+ if (!cgc)
+ break;
+ if (level) {
+ pcgc = find_ancestor_cgrp_ctx(cgrp, level - 1);
+ if (!pcgc)
+ break;
+ }
+
+ /*
+ * We need the propagation protected by a lock to synchronize
+ * against weight changes. There's no reason to drop the lock at
+ * each level but bpf_spin_lock() doesn't want any function
+ * calls while locked.
+ */
+ bpf_spin_lock(&cgv_tree_lock);
+
+ if (runnable) {
+ if (!cgc->nr_active++) {
+ updated = true;
+ if (pcgc) {
+ propagate = true;
+ pcgc->child_weight_sum += cgc->weight;
+ }
+ }
+ } else {
+ if (!--cgc->nr_active) {
+ updated = true;
+ if (pcgc) {
+ propagate = true;
+ pcgc->child_weight_sum -= cgc->weight;
+ }
+ }
+ }
+
+ bpf_spin_unlock(&cgv_tree_lock);
+
+ if (!propagate)
+ break;
+ }
+
+ if (updated)
+ __sync_fetch_and_add(&hweight_gen, 1);
+
+ if (runnable)
+ cgrp_refresh_hweight(cgrp, cgc);
+}
+
+void BPF_STRUCT_OPS(fcg_runnable, struct task_struct *p, u64 enq_flags)
+{
+ struct cgroup *cgrp;
+
+ cgrp = __COMPAT_scx_bpf_task_cgroup(p);
+ update_active_weight_sums(cgrp, true);
+ bpf_cgroup_release(cgrp);
+}
+
+void BPF_STRUCT_OPS(fcg_running, struct task_struct *p)
+{
+ struct cgroup *cgrp;
+ struct fcg_cgrp_ctx *cgc;
+
+ if (fifo_sched)
+ return;
+
+ cgrp = __COMPAT_scx_bpf_task_cgroup(p);
+ cgc = find_cgrp_ctx(cgrp);
+ if (cgc) {
+ /*
+ * @cgc->tvtime_now 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(cgc->tvtime_now, p->scx.dsq_vtime))
+ cgc->tvtime_now = p->scx.dsq_vtime;
+ }
+ bpf_cgroup_release(cgrp);
+}
+
+void BPF_STRUCT_OPS(fcg_stopping, struct task_struct *p, bool runnable)
+{
+ struct fcg_task_ctx *taskc;
+ struct cgroup *cgrp;
+ struct fcg_cgrp_ctx *cgc;
+
+ /*
+ * 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.
+ */
+ if (!fifo_sched)
+ p->scx.dsq_vtime +=
+ (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+
+ taskc = bpf_task_storage_get(&task_ctx, p, 0, 0);
+ if (!taskc) {
+ scx_bpf_error("task_ctx lookup failed");
+ return;
+ }
+
+ if (!taskc->bypassed_at)
+ return;
+
+ cgrp = __COMPAT_scx_bpf_task_cgroup(p);
+ cgc = find_cgrp_ctx(cgrp);
+ if (cgc) {
+ __sync_fetch_and_add(&cgc->cvtime_delta,
+ p->se.sum_exec_runtime - taskc->bypassed_at);
+ taskc->bypassed_at = 0;
+ }
+ bpf_cgroup_release(cgrp);
+}
+
+void BPF_STRUCT_OPS(fcg_quiescent, struct task_struct *p, u64 deq_flags)
+{
+ struct cgroup *cgrp;
+
+ cgrp = __COMPAT_scx_bpf_task_cgroup(p);
+ update_active_weight_sums(cgrp, false);
+ bpf_cgroup_release(cgrp);
+}
+
+void BPF_STRUCT_OPS(fcg_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
+{
+ struct fcg_cgrp_ctx *cgc, *pcgc = NULL;
+
+ cgc = find_cgrp_ctx(cgrp);
+ if (!cgc)
+ return;
+
+ if (cgrp->level) {
+ pcgc = find_ancestor_cgrp_ctx(cgrp, cgrp->level - 1);
+ if (!pcgc)
+ return;
+ }
+
+ bpf_spin_lock(&cgv_tree_lock);
+ if (pcgc && cgc->nr_active)
+ pcgc->child_weight_sum += (s64)weight - cgc->weight;
+ cgc->weight = weight;
+ bpf_spin_unlock(&cgv_tree_lock);
+}
+
+static bool try_pick_next_cgroup(u64 *cgidp)
+{
+ struct bpf_rb_node *rb_node;
+ struct cgv_node_stash *stash;
+ struct cgv_node *cgv_node;
+ struct fcg_cgrp_ctx *cgc;
+ struct cgroup *cgrp;
+ u64 cgid;
+
+ /* pop the front cgroup and wind cvtime_now accordingly */
+ bpf_spin_lock(&cgv_tree_lock);
+
+ rb_node = bpf_rbtree_first(&cgv_tree);
+ if (!rb_node) {
+ bpf_spin_unlock(&cgv_tree_lock);
+ stat_inc(FCG_STAT_PNC_NO_CGRP);
+ *cgidp = 0;
+ return true;
+ }
+
+ rb_node = bpf_rbtree_remove(&cgv_tree, rb_node);
+ bpf_spin_unlock(&cgv_tree_lock);
+
+ if (!rb_node) {
+ /*
+ * This should never happen. bpf_rbtree_first() was called
+ * above while the tree lock was held, so the node should
+ * always be present.
+ */
+ scx_bpf_error("node could not be removed");
+ return true;
+ }
+
+ cgv_node = container_of(rb_node, struct cgv_node, rb_node);
+ cgid = cgv_node->cgid;
+
+ if (vtime_before(cvtime_now, cgv_node->cvtime))
+ cvtime_now = cgv_node->cvtime;
+
+ /*
+ * If lookup fails, the cgroup's gone. Free and move on. See
+ * fcg_cgroup_exit().
+ */
+ cgrp = bpf_cgroup_from_id(cgid);
+ if (!cgrp) {
+ stat_inc(FCG_STAT_PNC_GONE);
+ goto out_free;
+ }
+
+ cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0);
+ if (!cgc) {
+ bpf_cgroup_release(cgrp);
+ stat_inc(FCG_STAT_PNC_GONE);
+ goto out_free;
+ }
+
+ if (!scx_bpf_consume(cgid)) {
+ bpf_cgroup_release(cgrp);
+ stat_inc(FCG_STAT_PNC_EMPTY);
+ goto out_stash;
+ }
+
+ /*
+ * Successfully consumed from the cgroup. This will be our current
+ * cgroup for the new slice. Refresh its hweight.
+ */
+ cgrp_refresh_hweight(cgrp, cgc);
+
+ bpf_cgroup_release(cgrp);
+
+ /*
+ * As the cgroup may have more tasks, add it back to the rbtree. Note
+ * that here we charge the full slice upfront and then exact later
+ * according to the actual consumption. This prevents lowpri thundering
+ * herd from saturating the machine.
+ */
+ bpf_spin_lock(&cgv_tree_lock);
+ cgv_node->cvtime += cgrp_slice_ns * FCG_HWEIGHT_ONE / (cgc->hweight ?: 1);
+ cgrp_cap_budget(cgv_node, cgc);
+ bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less);
+ bpf_spin_unlock(&cgv_tree_lock);
+
+ *cgidp = cgid;
+ stat_inc(FCG_STAT_PNC_NEXT);
+ return true;
+
+out_stash:
+ stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid);
+ if (!stash) {
+ stat_inc(FCG_STAT_PNC_GONE);
+ goto out_free;
+ }
+
+ /*
+ * Paired with cmpxchg in cgrp_enqueued(). If they see the following
+ * transition, they'll enqueue the cgroup. If they are earlier, we'll
+ * see their task in the dq below and requeue the cgroup.
+ */
+ __sync_val_compare_and_swap(&cgc->queued, 1, 0);
+
+ if (scx_bpf_dsq_nr_queued(cgid)) {
+ bpf_spin_lock(&cgv_tree_lock);
+ bpf_rbtree_add(&cgv_tree, &cgv_node->rb_node, cgv_node_less);
+ bpf_spin_unlock(&cgv_tree_lock);
+ stat_inc(FCG_STAT_PNC_RACE);
+ } else {
+ cgv_node = bpf_kptr_xchg(&stash->node, cgv_node);
+ if (cgv_node) {
+ scx_bpf_error("unexpected !NULL cgv_node stash");
+ goto out_free;
+ }
+ }
+
+ return false;
+
+out_free:
+ bpf_obj_drop(cgv_node);
+ return false;
+}
+
+void BPF_STRUCT_OPS(fcg_dispatch, s32 cpu, struct task_struct *prev)
+{
+ struct fcg_cpu_ctx *cpuc;
+ struct fcg_cgrp_ctx *cgc;
+ struct cgroup *cgrp;
+ u64 now = bpf_ktime_get_ns();
+ bool picked_next = false;
+
+ cpuc = find_cpu_ctx();
+ if (!cpuc)
+ return;
+
+ if (!cpuc->cur_cgid)
+ goto pick_next_cgroup;
+
+ if (vtime_before(now, cpuc->cur_at + cgrp_slice_ns)) {
+ if (scx_bpf_consume(cpuc->cur_cgid)) {
+ stat_inc(FCG_STAT_CNS_KEEP);
+ return;
+ }
+ stat_inc(FCG_STAT_CNS_EMPTY);
+ } else {
+ stat_inc(FCG_STAT_CNS_EXPIRE);
+ }
+
+ /*
+ * The current cgroup is expiring. It was already charged a full slice.
+ * Calculate the actual usage and accumulate the delta.
+ */
+ cgrp = bpf_cgroup_from_id(cpuc->cur_cgid);
+ if (!cgrp) {
+ stat_inc(FCG_STAT_CNS_GONE);
+ goto pick_next_cgroup;
+ }
+
+ cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0, 0);
+ if (cgc) {
+ /*
+ * We want to update the vtime delta and then look for the next
+ * cgroup to execute but the latter needs to be done in a loop
+ * and we can't keep the lock held. Oh well...
+ */
+ bpf_spin_lock(&cgv_tree_lock);
+ __sync_fetch_and_add(&cgc->cvtime_delta,
+ (cpuc->cur_at + cgrp_slice_ns - now) *
+ FCG_HWEIGHT_ONE / (cgc->hweight ?: 1));
+ bpf_spin_unlock(&cgv_tree_lock);
+ } else {
+ stat_inc(FCG_STAT_CNS_GONE);
+ }
+
+ bpf_cgroup_release(cgrp);
+
+pick_next_cgroup:
+ cpuc->cur_at = now;
+
+ if (scx_bpf_consume(FALLBACK_DSQ)) {
+ cpuc->cur_cgid = 0;
+ return;
+ }
+
+ bpf_repeat(CGROUP_MAX_RETRIES) {
+ if (try_pick_next_cgroup(&cpuc->cur_cgid)) {
+ picked_next = true;
+ break;
+ }
+ }
+
+ /*
+ * This only happens if try_pick_next_cgroup() races against enqueue
+ * path for more than CGROUP_MAX_RETRIES times, which is extremely
+ * unlikely and likely indicates an underlying bug. There shouldn't be
+ * any stall risk as the race is against enqueue.
+ */
+ if (!picked_next)
+ stat_inc(FCG_STAT_PNC_FAIL);
+}
+
+s32 BPF_STRUCT_OPS(fcg_init_task, struct task_struct *p,
+ struct scx_init_task_args *args)
+{
+ struct fcg_task_ctx *taskc;
+ struct fcg_cgrp_ctx *cgc;
+
+ /*
+ * @p is new. Let's ensure that its task_ctx is available. We can sleep
+ * in this function and the following will automatically use GFP_KERNEL.
+ */
+ taskc = bpf_task_storage_get(&task_ctx, p, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!taskc)
+ return -ENOMEM;
+
+ taskc->bypassed_at = 0;
+
+ if (!(cgc = find_cgrp_ctx(args->cgroup)))
+ return -ENOENT;
+
+ p->scx.dsq_vtime = cgc->tvtime_now;
+
+ return 0;
+}
+
+int BPF_STRUCT_OPS_SLEEPABLE(fcg_cgroup_init, struct cgroup *cgrp,
+ struct scx_cgroup_init_args *args)
+{
+ struct fcg_cgrp_ctx *cgc;
+ struct cgv_node *cgv_node;
+ struct cgv_node_stash empty_stash = {}, *stash;
+ u64 cgid = cgrp->kn->id;
+ int ret;
+
+ /*
+ * Technically incorrect as cgroup ID is full 64bit while dsq ID is
+ * 63bit. Should not be a problem in practice and easy to spot in the
+ * unlikely case that it breaks.
+ */
+ ret = scx_bpf_create_dsq(cgid, -1);
+ if (ret)
+ return ret;
+
+ cgc = bpf_cgrp_storage_get(&cgrp_ctx, cgrp, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!cgc) {
+ ret = -ENOMEM;
+ goto err_destroy_dsq;
+ }
+
+ cgc->weight = args->weight;
+ cgc->hweight = FCG_HWEIGHT_ONE;
+
+ ret = bpf_map_update_elem(&cgv_node_stash, &cgid, &empty_stash,
+ BPF_NOEXIST);
+ if (ret) {
+ if (ret != -ENOMEM)
+ scx_bpf_error("unexpected stash creation error (%d)",
+ ret);
+ goto err_destroy_dsq;
+ }
+
+ stash = bpf_map_lookup_elem(&cgv_node_stash, &cgid);
+ if (!stash) {
+ scx_bpf_error("unexpected cgv_node stash lookup failure");
+ ret = -ENOENT;
+ goto err_destroy_dsq;
+ }
+
+ cgv_node = bpf_obj_new(struct cgv_node);
+ if (!cgv_node) {
+ ret = -ENOMEM;
+ goto err_del_cgv_node;
+ }
+
+ cgv_node->cgid = cgid;
+ cgv_node->cvtime = cvtime_now;
+
+ cgv_node = bpf_kptr_xchg(&stash->node, cgv_node);
+ if (cgv_node) {
+ scx_bpf_error("unexpected !NULL cgv_node stash");
+ ret = -EBUSY;
+ goto err_drop;
+ }
+
+ return 0;
+
+err_drop:
+ bpf_obj_drop(cgv_node);
+err_del_cgv_node:
+ bpf_map_delete_elem(&cgv_node_stash, &cgid);
+err_destroy_dsq:
+ scx_bpf_destroy_dsq(cgid);
+ return ret;
+}
+
+void BPF_STRUCT_OPS(fcg_cgroup_exit, struct cgroup *cgrp)
+{
+ u64 cgid = cgrp->kn->id;
+
+ /*
+ * For now, there's no way find and remove the cgv_node if it's on the
+ * cgv_tree. Let's drain them in the dispatch path as they get popped
+ * off the front of the tree.
+ */
+ bpf_map_delete_elem(&cgv_node_stash, &cgid);
+ scx_bpf_destroy_dsq(cgid);
+}
+
+void BPF_STRUCT_OPS(fcg_cgroup_move, struct task_struct *p,
+ struct cgroup *from, struct cgroup *to)
+{
+ struct fcg_cgrp_ctx *from_cgc, *to_cgc;
+ s64 vtime_delta;
+
+ /* find_cgrp_ctx() triggers scx_ops_error() on lookup failures */
+ if (!(from_cgc = find_cgrp_ctx(from)) || !(to_cgc = find_cgrp_ctx(to)))
+ return;
+
+ vtime_delta = p->scx.dsq_vtime - from_cgc->tvtime_now;
+ p->scx.dsq_vtime = to_cgc->tvtime_now + vtime_delta;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(fcg_init)
+{
+ return scx_bpf_create_dsq(FALLBACK_DSQ, -1);
+}
+
+void BPF_STRUCT_OPS(fcg_exit, struct scx_exit_info *ei)
+{
+ UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(flatcg_ops,
+ .select_cpu = (void *)fcg_select_cpu,
+ .enqueue = (void *)fcg_enqueue,
+ .dispatch = (void *)fcg_dispatch,
+ .runnable = (void *)fcg_runnable,
+ .running = (void *)fcg_running,
+ .stopping = (void *)fcg_stopping,
+ .quiescent = (void *)fcg_quiescent,
+ .init_task = (void *)fcg_init_task,
+ .cgroup_set_weight = (void *)fcg_cgroup_set_weight,
+ .cgroup_init = (void *)fcg_cgroup_init,
+ .cgroup_exit = (void *)fcg_cgroup_exit,
+ .cgroup_move = (void *)fcg_cgroup_move,
+ .init = (void *)fcg_init,
+ .exit = (void *)fcg_exit,
+ .flags = SCX_OPS_HAS_CGROUP_WEIGHT | SCX_OPS_ENQ_EXITING,
+ .name = "flatcg");
diff --git a/tools/sched_ext/scx_flatcg.c b/tools/sched_ext/scx_flatcg.c
new file mode 100644
index 000000000000..5d24ca9c29d9
--- /dev/null
+++ b/tools/sched_ext/scx_flatcg.c
@@ -0,0 +1,233 @@
+/* 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>
+ */
+#include <stdio.h>
+#include <signal.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <limits.h>
+#include <inttypes.h>
+#include <fcntl.h>
+#include <time.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_flatcg.h"
+#include "scx_flatcg.bpf.skel.h"
+
+#ifndef FILEID_KERNFS
+#define FILEID_KERNFS 0xfe
+#endif
+
+const char help_fmt[] =
+"A flattened cgroup hierarchy sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-s SLICE_US] [-i INTERVAL] [-f] [-v]\n"
+"\n"
+" -s SLICE_US Override slice duration\n"
+" -i INTERVAL Report interval\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 dummy)
+{
+ exit_req = 1;
+}
+
+static float read_cpu_util(__u64 *last_sum, __u64 *last_idle)
+{
+ FILE *fp;
+ char buf[4096];
+ char *line, *cur = NULL, *tok;
+ __u64 sum = 0, idle = 0;
+ __u64 delta_sum, delta_idle;
+ int idx;
+
+ fp = fopen("/proc/stat", "r");
+ if (!fp) {
+ perror("fopen(\"/proc/stat\")");
+ return 0.0;
+ }
+
+ if (!fgets(buf, sizeof(buf), fp)) {
+ perror("fgets(\"/proc/stat\")");
+ fclose(fp);
+ return 0.0;
+ }
+ fclose(fp);
+
+ line = buf;
+ for (idx = 0; (tok = strtok_r(line, " \n", &cur)); idx++) {
+ char *endp = NULL;
+ __u64 v;
+
+ if (idx == 0) {
+ line = NULL;
+ continue;
+ }
+ v = strtoull(tok, &endp, 0);
+ if (!endp || *endp != '\0') {
+ fprintf(stderr, "failed to parse %dth field of /proc/stat (\"%s\")\n",
+ idx, tok);
+ continue;
+ }
+ sum += v;
+ if (idx == 4)
+ idle = v;
+ }
+
+ delta_sum = sum - *last_sum;
+ delta_idle = idle - *last_idle;
+ *last_sum = sum;
+ *last_idle = idle;
+
+ return delta_sum ? (float)(delta_sum - delta_idle) / delta_sum : 0.0;
+}
+
+static void fcg_read_stats(struct scx_flatcg *skel, __u64 *stats)
+{
+ __u64 cnts[FCG_NR_STATS][skel->rodata->nr_cpus];
+ __u32 idx;
+
+ memset(stats, 0, sizeof(stats[0]) * FCG_NR_STATS);
+
+ for (idx = 0; idx < FCG_NR_STATS; 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 < skel->rodata->nr_cpus; cpu++)
+ stats[idx] += cnts[idx][cpu];
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct scx_flatcg *skel;
+ struct bpf_link *link;
+ struct timespec intv_ts = { .tv_sec = 2, .tv_nsec = 0 };
+ bool dump_cgrps = false;
+ __u64 last_cpu_sum = 0, last_cpu_idle = 0;
+ __u64 last_stats[FCG_NR_STATS] = {};
+ unsigned long seq = 0;
+ __s32 opt;
+ __u64 ecode;
+
+ libbpf_set_print(libbpf_print_fn);
+ signal(SIGINT, sigint_handler);
+ signal(SIGTERM, sigint_handler);
+restart:
+ skel = SCX_OPS_OPEN(flatcg_ops, scx_flatcg);
+
+ skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+ while ((opt = getopt(argc, argv, "s:i:dfvh")) != -1) {
+ double v;
+
+ switch (opt) {
+ case 's':
+ v = strtod(optarg, NULL);
+ skel->rodata->cgrp_slice_ns = v * 1000;
+ break;
+ case 'i':
+ v = strtod(optarg, NULL);
+ intv_ts.tv_sec = v;
+ intv_ts.tv_nsec = (v - (float)intv_ts.tv_sec) * 1000000000;
+ break;
+ case 'd':
+ dump_cgrps = true;
+ break;
+ case 'f':
+ skel->rodata->fifo_sched = true;
+ break;
+ case 'v':
+ verbose = true;
+ break;
+ case 'h':
+ default:
+ fprintf(stderr, help_fmt, basename(argv[0]));
+ return opt != 'h';
+ }
+ }
+
+ printf("slice=%.1lfms intv=%.1lfs dump_cgrps=%d",
+ (double)skel->rodata->cgrp_slice_ns / 1000000.0,
+ (double)intv_ts.tv_sec + (double)intv_ts.tv_nsec / 1000000000.0,
+ dump_cgrps);
+
+ SCX_OPS_LOAD(skel, flatcg_ops, scx_flatcg, uei);
+ link = SCX_OPS_ATTACH(skel, flatcg_ops, scx_flatcg);
+
+ while (!exit_req && !UEI_EXITED(skel, uei)) {
+ __u64 acc_stats[FCG_NR_STATS];
+ __u64 stats[FCG_NR_STATS];
+ float cpu_util;
+ int i;
+
+ cpu_util = read_cpu_util(&last_cpu_sum, &last_cpu_idle);
+
+ fcg_read_stats(skel, acc_stats);
+ for (i = 0; i < FCG_NR_STATS; i++)
+ stats[i] = acc_stats[i] - last_stats[i];
+
+ memcpy(last_stats, acc_stats, sizeof(acc_stats));
+
+ printf("\n[SEQ %6lu cpu=%5.1lf hweight_gen=%" PRIu64 "]\n",
+ seq++, cpu_util * 100.0, skel->data->hweight_gen);
+ printf(" act:%6llu deact:%6llu global:%6llu local:%6llu\n",
+ stats[FCG_STAT_ACT],
+ stats[FCG_STAT_DEACT],
+ stats[FCG_STAT_GLOBAL],
+ stats[FCG_STAT_LOCAL]);
+ printf("HWT cache:%6llu update:%6llu skip:%6llu race:%6llu\n",
+ stats[FCG_STAT_HWT_CACHE],
+ stats[FCG_STAT_HWT_UPDATES],
+ stats[FCG_STAT_HWT_SKIP],
+ stats[FCG_STAT_HWT_RACE]);
+ printf("ENQ skip:%6llu race:%6llu\n",
+ stats[FCG_STAT_ENQ_SKIP],
+ stats[FCG_STAT_ENQ_RACE]);
+ printf("CNS keep:%6llu expire:%6llu empty:%6llu gone:%6llu\n",
+ stats[FCG_STAT_CNS_KEEP],
+ stats[FCG_STAT_CNS_EXPIRE],
+ stats[FCG_STAT_CNS_EMPTY],
+ stats[FCG_STAT_CNS_GONE]);
+ printf("PNC next:%6llu empty:%6llu nocgrp:%6llu gone:%6llu race:%6llu fail:%6llu\n",
+ stats[FCG_STAT_PNC_NEXT],
+ stats[FCG_STAT_PNC_EMPTY],
+ stats[FCG_STAT_PNC_NO_CGRP],
+ stats[FCG_STAT_PNC_GONE],
+ stats[FCG_STAT_PNC_RACE],
+ stats[FCG_STAT_PNC_FAIL]);
+ printf("BAD remove:%6llu\n",
+ acc_stats[FCG_STAT_BAD_REMOVAL]);
+ fflush(stdout);
+
+ nanosleep(&intv_ts, NULL);
+ }
+
+ bpf_link__destroy(link);
+ ecode = UEI_REPORT(skel, uei);
+ scx_flatcg__destroy(skel);
+
+ if (UEI_ECODE_RESTART(ecode))
+ goto restart;
+ return 0;
+}
diff --git a/tools/sched_ext/scx_flatcg.h b/tools/sched_ext/scx_flatcg.h
new file mode 100644
index 000000000000..6f2ea50acb1c
--- /dev/null
+++ b/tools/sched_ext/scx_flatcg.h
@@ -0,0 +1,51 @@
+#ifndef __SCX_EXAMPLE_FLATCG_H
+#define __SCX_EXAMPLE_FLATCG_H
+
+enum {
+ FCG_HWEIGHT_ONE = 1LLU << 16,
+};
+
+enum fcg_stat_idx {
+ FCG_STAT_ACT,
+ FCG_STAT_DEACT,
+ FCG_STAT_LOCAL,
+ FCG_STAT_GLOBAL,
+
+ FCG_STAT_HWT_UPDATES,
+ FCG_STAT_HWT_CACHE,
+ FCG_STAT_HWT_SKIP,
+ FCG_STAT_HWT_RACE,
+
+ FCG_STAT_ENQ_SKIP,
+ FCG_STAT_ENQ_RACE,
+
+ FCG_STAT_CNS_KEEP,
+ FCG_STAT_CNS_EXPIRE,
+ FCG_STAT_CNS_EMPTY,
+ FCG_STAT_CNS_GONE,
+
+ FCG_STAT_PNC_NO_CGRP,
+ FCG_STAT_PNC_NEXT,
+ FCG_STAT_PNC_EMPTY,
+ FCG_STAT_PNC_GONE,
+ FCG_STAT_PNC_RACE,
+ FCG_STAT_PNC_FAIL,
+
+ FCG_STAT_BAD_REMOVAL,
+
+ FCG_NR_STATS,
+};
+
+struct fcg_cgrp_ctx {
+ u32 nr_active;
+ u32 nr_runnable;
+ u32 queued;
+ u32 weight;
+ u32 hweight;
+ u64 child_weight_sum;
+ u64 hweight_gen;
+ s64 cvtime_delta;
+ u64 tvtime_now;
+};
+
+#endif /* __SCX_EXAMPLE_FLATCG_H */
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
new file mode 100644
index 000000000000..5b39bee9eb23
--- /dev/null
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -0,0 +1,813 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple five-level FIFO queue scheduler.
+ *
+ * There are five FIFOs implemented using BPF_MAP_TYPE_QUEUE. A task gets
+ * assigned to one depending on its compound weight. Each CPU round robins
+ * through the FIFOs and dispatches more from FIFOs with higher indices - 1 from
+ * queue0, 2 from queue1, 4 from queue2 and so on.
+ *
+ * This scheduler demonstrates:
+ *
+ * - BPF-side queueing using PIDs.
+ * - Sleepable per-task storage allocation using ops.prep_enable().
+ * - Using ops.cpu_release() to handle a higher priority scheduling class taking
+ * the CPU away.
+ * - Core-sched support.
+ *
+ * This scheduler is primarily for demonstration and testing of sched_ext
+ * features and unlikely to be useful for actual workloads.
+ *
+ * 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>
+
+enum consts {
+ ONE_SEC_IN_NS = 1000000000,
+ SHARED_DSQ = 0,
+ HIGHPRI_DSQ = 1,
+ HIGHPRI_WEIGHT = 8668, /* this is what -20 maps to */
+};
+
+char _license[] SEC("license") = "GPL";
+
+const volatile u64 slice_ns = SCX_SLICE_DFL;
+const volatile u32 stall_user_nth;
+const volatile u32 stall_kernel_nth;
+const volatile u32 dsp_inf_loop_after;
+const volatile u32 dsp_batch;
+const volatile bool highpri_boosting;
+const volatile bool print_shared_dsq;
+const volatile s32 disallow_tgid;
+const volatile bool suppress_dump;
+
+u64 nr_highpri_queued;
+u32 test_error_cnt;
+
+UEI_DEFINE(uei);
+
+struct qmap {
+ __uint(type, BPF_MAP_TYPE_QUEUE);
+ __uint(max_entries, 4096);
+ __type(value, u32);
+} queue0 SEC(".maps"),
+ queue1 SEC(".maps"),
+ queue2 SEC(".maps"),
+ queue3 SEC(".maps"),
+ queue4 SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 5);
+ __type(key, int);
+ __array(values, struct qmap);
+} queue_arr SEC(".maps") = {
+ .values = {
+ [0] = &queue0,
+ [1] = &queue1,
+ [2] = &queue2,
+ [3] = &queue3,
+ [4] = &queue4,
+ },
+};
+
+/*
+ * If enabled, CPU performance target is set according to the queue index
+ * according to the following table.
+ */
+static const u32 qidx_to_cpuperf_target[] = {
+ [0] = SCX_CPUPERF_ONE * 0 / 4,
+ [1] = SCX_CPUPERF_ONE * 1 / 4,
+ [2] = SCX_CPUPERF_ONE * 2 / 4,
+ [3] = SCX_CPUPERF_ONE * 3 / 4,
+ [4] = SCX_CPUPERF_ONE * 4 / 4,
+};
+
+/*
+ * Per-queue sequence numbers to implement core-sched ordering.
+ *
+ * Tail seq is assigned to each queued task and incremented. Head seq tracks the
+ * sequence number of the latest dispatched task. The distance between the a
+ * task's seq and the associated queue's head seq is called the queue distance
+ * and used when comparing two tasks for ordering. See qmap_core_sched_before().
+ */
+static u64 core_sched_head_seqs[5];
+static u64 core_sched_tail_seqs[5];
+
+/* Per-task scheduling context */
+struct task_ctx {
+ bool force_local; /* Dispatch directly to local_dsq */
+ bool highpri;
+ u64 core_sched_seq;
+};
+
+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");
+
+struct cpu_ctx {
+ u64 dsp_idx; /* dispatch index */
+ u64 dsp_cnt; /* remaining count */
+ u32 avg_weight;
+ u32 cpuperf_target;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, u32);
+ __type(value, struct cpu_ctx);
+} cpu_ctx_stor SEC(".maps");
+
+/* Statistics */
+u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued, nr_ddsp_from_enq;
+u64 nr_core_sched_execed;
+u64 nr_expedited_local, nr_expedited_remote, nr_expedited_lost, nr_expedited_from_timer;
+u32 cpuperf_min, cpuperf_avg, cpuperf_max;
+u32 cpuperf_target_min, cpuperf_target_avg, cpuperf_target_max;
+
+static s32 pick_direct_dispatch_cpu(struct task_struct *p, s32 prev_cpu)
+{
+ s32 cpu;
+
+ if (p->nr_cpus_allowed == 1 ||
+ scx_bpf_test_and_clear_cpu_idle(prev_cpu))
+ return prev_cpu;
+
+ cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+ if (cpu >= 0)
+ return cpu;
+
+ return -1;
+}
+
+static struct task_ctx *lookup_task_ctx(struct task_struct *p)
+{
+ struct task_ctx *tctx;
+
+ if (!(tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) {
+ scx_bpf_error("task_ctx lookup failed");
+ return NULL;
+ }
+ return tctx;
+}
+
+s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p,
+ s32 prev_cpu, u64 wake_flags)
+{
+ struct task_ctx *tctx;
+ s32 cpu;
+
+ if (!(tctx = lookup_task_ctx(p)))
+ return -ESRCH;
+
+ cpu = pick_direct_dispatch_cpu(p, prev_cpu);
+
+ if (cpu >= 0) {
+ tctx->force_local = true;
+ return cpu;
+ } else {
+ return prev_cpu;
+ }
+}
+
+static int weight_to_idx(u32 weight)
+{
+ /* Coarsely map the compound weight to a FIFO. */
+ if (weight <= 25)
+ return 0;
+ else if (weight <= 50)
+ return 1;
+ else if (weight < 200)
+ return 2;
+ else if (weight < 400)
+ return 3;
+ else
+ return 4;
+}
+
+void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
+{
+ static u32 user_cnt, kernel_cnt;
+ struct task_ctx *tctx;
+ u32 pid = p->pid;
+ int idx = weight_to_idx(p->scx.weight);
+ void *ring;
+ s32 cpu;
+
+ if (p->flags & PF_KTHREAD) {
+ if (stall_kernel_nth && !(++kernel_cnt % stall_kernel_nth))
+ return;
+ } else {
+ if (stall_user_nth && !(++user_cnt % stall_user_nth))
+ return;
+ }
+
+ if (test_error_cnt && !--test_error_cnt)
+ scx_bpf_error("test triggering error");
+
+ if (!(tctx = lookup_task_ctx(p)))
+ return;
+
+ /*
+ * All enqueued tasks must have their core_sched_seq updated for correct
+ * core-sched ordering, which is why %SCX_OPS_ENQ_LAST is specified in
+ * qmap_ops.flags.
+ */
+ tctx->core_sched_seq = core_sched_tail_seqs[idx]++;
+
+ /*
+ * If qmap_select_cpu() is telling us to or this is the last runnable
+ * task on the CPU, enqueue locally.
+ */
+ if (tctx->force_local || (enq_flags & SCX_ENQ_LAST)) {
+ tctx->force_local = false;
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, enq_flags);
+ return;
+ }
+
+ /* if !WAKEUP, select_cpu() wasn't called, try direct dispatch */
+ if (!(enq_flags & SCX_ENQ_WAKEUP) &&
+ (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(p))) >= 0) {
+ __sync_fetch_and_add(&nr_ddsp_from_enq, 1);
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, slice_ns, enq_flags);
+ return;
+ }
+
+ /*
+ * If the task was re-enqueued due to the CPU being preempted by a
+ * higher priority scheduling class, just re-enqueue the task directly
+ * on the global DSQ. As we want another CPU to pick it up, find and
+ * kick an idle CPU.
+ */
+ if (enq_flags & SCX_ENQ_REENQ) {
+ s32 cpu;
+
+ scx_bpf_dispatch(p, SHARED_DSQ, 0, enq_flags);
+ cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+ if (cpu >= 0)
+ scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+ return;
+ }
+
+ ring = bpf_map_lookup_elem(&queue_arr, &idx);
+ if (!ring) {
+ scx_bpf_error("failed to find ring %d", idx);
+ return;
+ }
+
+ /* Queue on the selected FIFO. If the FIFO overflows, punt to global. */
+ if (bpf_map_push_elem(ring, &pid, 0)) {
+ scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, enq_flags);
+ return;
+ }
+
+ if (highpri_boosting && p->scx.weight >= HIGHPRI_WEIGHT) {
+ tctx->highpri = true;
+ __sync_fetch_and_add(&nr_highpri_queued, 1);
+ }
+ __sync_fetch_and_add(&nr_enqueued, 1);
+}
+
+/*
+ * The BPF queue map doesn't support removal and sched_ext can handle spurious
+ * dispatches. qmap_dequeue() is only used to collect statistics.
+ */
+void BPF_STRUCT_OPS(qmap_dequeue, struct task_struct *p, u64 deq_flags)
+{
+ __sync_fetch_and_add(&nr_dequeued, 1);
+ if (deq_flags & SCX_DEQ_CORE_SCHED_EXEC)
+ __sync_fetch_and_add(&nr_core_sched_execed, 1);
+}
+
+static void update_core_sched_head_seq(struct task_struct *p)
+{
+ int idx = weight_to_idx(p->scx.weight);
+ struct task_ctx *tctx;
+
+ if ((tctx = lookup_task_ctx(p)))
+ core_sched_head_seqs[idx] = tctx->core_sched_seq;
+}
+
+/*
+ * To demonstrate the use of scx_bpf_dispatch_from_dsq(), implement silly
+ * selective priority boosting mechanism by scanning SHARED_DSQ looking for
+ * highpri tasks, moving them to HIGHPRI_DSQ and then consuming them first. This
+ * makes minor difference only when dsp_batch is larger than 1.
+ *
+ * scx_bpf_dispatch[_vtime]_from_dsq() are allowed both from ops.dispatch() and
+ * non-rq-lock holding BPF programs. As demonstration, this function is called
+ * from qmap_dispatch() and monitor_timerfn().
+ */
+static bool dispatch_highpri(bool from_timer)
+{
+ struct task_struct *p;
+ s32 this_cpu = bpf_get_smp_processor_id();
+
+ /* scan SHARED_DSQ and move highpri tasks to HIGHPRI_DSQ */
+ bpf_for_each(scx_dsq, p, SHARED_DSQ, 0) {
+ static u64 highpri_seq;
+ struct task_ctx *tctx;
+
+ if (!(tctx = lookup_task_ctx(p)))
+ return false;
+
+ if (tctx->highpri) {
+ /* exercise the set_*() and vtime interface too */
+ __COMPAT_scx_bpf_dispatch_from_dsq_set_slice(
+ BPF_FOR_EACH_ITER, slice_ns * 2);
+ __COMPAT_scx_bpf_dispatch_from_dsq_set_vtime(
+ BPF_FOR_EACH_ITER, highpri_seq++);
+ __COMPAT_scx_bpf_dispatch_vtime_from_dsq(
+ BPF_FOR_EACH_ITER, p, HIGHPRI_DSQ, 0);
+ }
+ }
+
+ /*
+ * Scan HIGHPRI_DSQ and dispatch until a task that can run on this CPU
+ * is found.
+ */
+ bpf_for_each(scx_dsq, p, HIGHPRI_DSQ, 0) {
+ bool dispatched = false;
+ s32 cpu;
+
+ if (bpf_cpumask_test_cpu(this_cpu, p->cpus_ptr))
+ cpu = this_cpu;
+ else
+ cpu = scx_bpf_pick_any_cpu(p->cpus_ptr, 0);
+
+ if (__COMPAT_scx_bpf_dispatch_from_dsq(BPF_FOR_EACH_ITER, p,
+ SCX_DSQ_LOCAL_ON | cpu,
+ SCX_ENQ_PREEMPT)) {
+ if (cpu == this_cpu) {
+ dispatched = true;
+ __sync_fetch_and_add(&nr_expedited_local, 1);
+ } else {
+ __sync_fetch_and_add(&nr_expedited_remote, 1);
+ }
+ if (from_timer)
+ __sync_fetch_and_add(&nr_expedited_from_timer, 1);
+ } else {
+ __sync_fetch_and_add(&nr_expedited_lost, 1);
+ }
+
+ if (dispatched)
+ return true;
+ }
+
+ return false;
+}
+
+void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
+{
+ struct task_struct *p;
+ struct cpu_ctx *cpuc;
+ u32 zero = 0, batch = dsp_batch ?: 1;
+ void *fifo;
+ s32 i, pid;
+
+ if (dispatch_highpri(false))
+ return;
+
+ if (!nr_highpri_queued && scx_bpf_consume(SHARED_DSQ))
+ return;
+
+ if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) {
+ /*
+ * PID 2 should be kthreadd which should mostly be idle and off
+ * the scheduler. Let's keep dispatching it to force the kernel
+ * to call this function over and over again.
+ */
+ p = bpf_task_from_pid(2);
+ if (p) {
+ scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, 0);
+ bpf_task_release(p);
+ return;
+ }
+ }
+
+ if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) {
+ scx_bpf_error("failed to look up cpu_ctx");
+ return;
+ }
+
+ for (i = 0; i < 5; i++) {
+ /* Advance the dispatch cursor and pick the fifo. */
+ if (!cpuc->dsp_cnt) {
+ cpuc->dsp_idx = (cpuc->dsp_idx + 1) % 5;
+ cpuc->dsp_cnt = 1 << cpuc->dsp_idx;
+ }
+
+ fifo = bpf_map_lookup_elem(&queue_arr, &cpuc->dsp_idx);
+ if (!fifo) {
+ scx_bpf_error("failed to find ring %llu", cpuc->dsp_idx);
+ return;
+ }
+
+ /* Dispatch or advance. */
+ bpf_repeat(BPF_MAX_LOOPS) {
+ struct task_ctx *tctx;
+
+ if (bpf_map_pop_elem(fifo, &pid))
+ break;
+
+ p = bpf_task_from_pid(pid);
+ if (!p)
+ continue;
+
+ if (!(tctx = lookup_task_ctx(p))) {
+ bpf_task_release(p);
+ return;
+ }
+
+ if (tctx->highpri)
+ __sync_fetch_and_sub(&nr_highpri_queued, 1);
+
+ update_core_sched_head_seq(p);
+ __sync_fetch_and_add(&nr_dispatched, 1);
+
+ scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, 0);
+ bpf_task_release(p);
+
+ batch--;
+ cpuc->dsp_cnt--;
+ if (!batch || !scx_bpf_dispatch_nr_slots()) {
+ if (dispatch_highpri(false))
+ return;
+ scx_bpf_consume(SHARED_DSQ);
+ return;
+ }
+ if (!cpuc->dsp_cnt)
+ break;
+ }
+
+ cpuc->dsp_cnt = 0;
+ }
+}
+
+void BPF_STRUCT_OPS(qmap_tick, struct task_struct *p)
+{
+ struct cpu_ctx *cpuc;
+ u32 zero = 0;
+ int idx;
+
+ if (!(cpuc = bpf_map_lookup_elem(&cpu_ctx_stor, &zero))) {
+ scx_bpf_error("failed to look up cpu_ctx");
+ return;
+ }
+
+ /*
+ * Use the running avg of weights to select the target cpuperf level.
+ * This is a demonstration of the cpuperf feature rather than a
+ * practical strategy to regulate CPU frequency.
+ */
+ cpuc->avg_weight = cpuc->avg_weight * 3 / 4 + p->scx.weight / 4;
+ idx = weight_to_idx(cpuc->avg_weight);
+ cpuc->cpuperf_target = qidx_to_cpuperf_target[idx];
+
+ scx_bpf_cpuperf_set(scx_bpf_task_cpu(p), cpuc->cpuperf_target);
+}
+
+/*
+ * The distance from the head of the queue scaled by the weight of the queue.
+ * The lower the number, the older the task and the higher the priority.
+ */
+static s64 task_qdist(struct task_struct *p)
+{
+ int idx = weight_to_idx(p->scx.weight);
+ struct task_ctx *tctx;
+ s64 qdist;
+
+ tctx = bpf_task_storage_get(&task_ctx_stor, p, 0, 0);
+ if (!tctx) {
+ scx_bpf_error("task_ctx lookup failed");
+ return 0;
+ }
+
+ qdist = tctx->core_sched_seq - core_sched_head_seqs[idx];
+
+ /*
+ * As queue index increments, the priority doubles. The queue w/ index 3
+ * is dispatched twice more frequently than 2. Reflect the difference by
+ * scaling qdists accordingly. Note that the shift amount needs to be
+ * flipped depending on the sign to avoid flipping priority direction.
+ */
+ if (qdist >= 0)
+ return qdist << (4 - idx);
+ else
+ return qdist << idx;
+}
+
+/*
+ * This is called to determine the task ordering when core-sched is picking
+ * tasks to execute on SMT siblings and should encode about the same ordering as
+ * the regular scheduling path. Use the priority-scaled distances from the head
+ * of the queues to compare the two tasks which should be consistent with the
+ * dispatch path behavior.
+ */
+bool BPF_STRUCT_OPS(qmap_core_sched_before,
+ struct task_struct *a, struct task_struct *b)
+{
+ return task_qdist(a) > task_qdist(b);
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args)
+{
+ u32 cnt;
+
+ /*
+ * Called when @cpu is taken by a higher priority scheduling class. This
+ * makes @cpu no longer available for executing sched_ext tasks. As we
+ * don't want the tasks in @cpu's local dsq to sit there until @cpu
+ * becomes available again, re-enqueue them into the global dsq. See
+ * %SCX_ENQ_REENQ handling in qmap_enqueue().
+ */
+ cnt = scx_bpf_reenqueue_local();
+ if (cnt)
+ __sync_fetch_and_add(&nr_reenqueued, cnt);
+}
+
+s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
+ struct scx_init_task_args *args)
+{
+ if (p->tgid == disallow_tgid)
+ p->scx.disallow = true;
+
+ /*
+ * @p is new. Let's ensure that its task_ctx is available. We can sleep
+ * in this function and the following will automatically use GFP_KERNEL.
+ */
+ if (bpf_task_storage_get(&task_ctx_stor, p, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE))
+ return 0;
+ else
+ return -ENOMEM;
+}
+
+void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx)
+{
+ s32 i, pid;
+
+ if (suppress_dump)
+ return;
+
+ bpf_for(i, 0, 5) {
+ void *fifo;
+
+ if (!(fifo = bpf_map_lookup_elem(&queue_arr, &i)))
+ return;
+
+ scx_bpf_dump("QMAP FIFO[%d]:", i);
+ bpf_repeat(4096) {
+ if (bpf_map_pop_elem(fifo, &pid))
+ break;
+ scx_bpf_dump(" %d", pid);
+ }
+ scx_bpf_dump("\n");
+ }
+}
+
+void BPF_STRUCT_OPS(qmap_dump_cpu, struct scx_dump_ctx *dctx, s32 cpu, bool idle)
+{
+ u32 zero = 0;
+ struct cpu_ctx *cpuc;
+
+ if (suppress_dump || idle)
+ return;
+ if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, cpu)))
+ return;
+
+ scx_bpf_dump("QMAP: dsp_idx=%llu dsp_cnt=%llu avg_weight=%u cpuperf_target=%u",
+ cpuc->dsp_idx, cpuc->dsp_cnt, cpuc->avg_weight,
+ cpuc->cpuperf_target);
+}
+
+void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struct *p)
+{
+ struct task_ctx *taskc;
+
+ if (suppress_dump)
+ return;
+ if (!(taskc = bpf_task_storage_get(&task_ctx_stor, p, 0, 0)))
+ return;
+
+ scx_bpf_dump("QMAP: force_local=%d core_sched_seq=%llu",
+ taskc->force_local, taskc->core_sched_seq);
+}
+
+/*
+ * Print out the online and possible CPU map using bpf_printk() as a
+ * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
+ */
+static void print_cpus(void)
+{
+ const struct cpumask *possible, *online;
+ s32 cpu;
+ char buf[128] = "", *p;
+ int idx;
+
+ possible = scx_bpf_get_possible_cpumask();
+ online = scx_bpf_get_online_cpumask();
+
+ idx = 0;
+ bpf_for(cpu, 0, scx_bpf_nr_cpu_ids()) {
+ if (!(p = MEMBER_VPTR(buf, [idx++])))
+ break;
+ if (bpf_cpumask_test_cpu(cpu, online))
+ *p++ = 'O';
+ else if (bpf_cpumask_test_cpu(cpu, possible))
+ *p++ = 'X';
+ else
+ *p++ = ' ';
+
+ if ((cpu & 7) == 7) {
+ if (!(p = MEMBER_VPTR(buf, [idx++])))
+ break;
+ *p++ = '|';
+ }
+ }
+ buf[sizeof(buf) - 1] = '\0';
+
+ scx_bpf_put_cpumask(online);
+ scx_bpf_put_cpumask(possible);
+
+ bpf_printk("CPUS: |%s", buf);
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_online, s32 cpu)
+{
+ bpf_printk("CPU %d coming online", cpu);
+ /* @cpu is already online at this point */
+ print_cpus();
+}
+
+void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu)
+{
+ bpf_printk("CPU %d going offline", cpu);
+ /* @cpu is still online at this point */
+ print_cpus();
+}
+
+struct monitor_timer {
+ struct bpf_timer timer;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, u32);
+ __type(value, struct monitor_timer);
+} monitor_timer SEC(".maps");
+
+/*
+ * Print out the min, avg and max performance levels of CPUs every second to
+ * demonstrate the cpuperf interface.
+ */
+static void monitor_cpuperf(void)
+{
+ u32 zero = 0, nr_cpu_ids;
+ u64 cap_sum = 0, cur_sum = 0, cur_min = SCX_CPUPERF_ONE, cur_max = 0;
+ u64 target_sum = 0, target_min = SCX_CPUPERF_ONE, target_max = 0;
+ const struct cpumask *online;
+ int i, nr_online_cpus = 0;
+
+ nr_cpu_ids = scx_bpf_nr_cpu_ids();
+ online = scx_bpf_get_online_cpumask();
+
+ bpf_for(i, 0, nr_cpu_ids) {
+ struct cpu_ctx *cpuc;
+ u32 cap, cur;
+
+ if (!bpf_cpumask_test_cpu(i, online))
+ continue;
+ nr_online_cpus++;
+
+ /* collect the capacity and current cpuperf */
+ cap = scx_bpf_cpuperf_cap(i);
+ cur = scx_bpf_cpuperf_cur(i);
+
+ cur_min = cur < cur_min ? cur : cur_min;
+ cur_max = cur > cur_max ? cur : cur_max;
+
+ /*
+ * $cur is relative to $cap. Scale it down accordingly so that
+ * it's in the same scale as other CPUs and $cur_sum/$cap_sum
+ * makes sense.
+ */
+ cur_sum += cur * cap / SCX_CPUPERF_ONE;
+ cap_sum += cap;
+
+ if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, i))) {
+ scx_bpf_error("failed to look up cpu_ctx");
+ goto out;
+ }
+
+ /* collect target */
+ cur = cpuc->cpuperf_target;
+ target_sum += cur;
+ target_min = cur < target_min ? cur : target_min;
+ target_max = cur > target_max ? cur : target_max;
+ }
+
+ cpuperf_min = cur_min;
+ cpuperf_avg = cur_sum * SCX_CPUPERF_ONE / cap_sum;
+ cpuperf_max = cur_max;
+
+ cpuperf_target_min = target_min;
+ cpuperf_target_avg = target_sum / nr_online_cpus;
+ cpuperf_target_max = target_max;
+out:
+ scx_bpf_put_cpumask(online);
+}
+
+/*
+ * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of
+ * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to
+ * see meaningful dumps in the trace pipe.
+ */
+static void dump_shared_dsq(void)
+{
+ struct task_struct *p;
+ s32 nr;
+
+ if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ)))
+ return;
+
+ bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr);
+
+ bpf_rcu_read_lock();
+ bpf_for_each(scx_dsq, p, SHARED_DSQ, SCX_DSQ_ITER_REV)
+ bpf_printk("%s[%d]", p->comm, p->pid);
+ bpf_rcu_read_unlock();
+}
+
+static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer)
+{
+ bpf_rcu_read_lock();
+ dispatch_highpri(true);
+ bpf_rcu_read_unlock();
+
+ monitor_cpuperf();
+
+ if (print_shared_dsq)
+ dump_shared_dsq();
+
+ bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
+ return 0;
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init)
+{
+ u32 key = 0;
+ struct bpf_timer *timer;
+ s32 ret;
+
+ print_cpus();
+
+ ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
+ if (ret)
+ return ret;
+
+ ret = scx_bpf_create_dsq(HIGHPRI_DSQ, -1);
+ if (ret)
+ return ret;
+
+ timer = bpf_map_lookup_elem(&monitor_timer, &key);
+ if (!timer)
+ return -ESRCH;
+
+ bpf_timer_init(timer, &monitor_timer, CLOCK_MONOTONIC);
+ bpf_timer_set_callback(timer, monitor_timerfn);
+
+ return bpf_timer_start(timer, ONE_SEC_IN_NS, 0);
+}
+
+void BPF_STRUCT_OPS(qmap_exit, struct scx_exit_info *ei)
+{
+ UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(qmap_ops,
+ .select_cpu = (void *)qmap_select_cpu,
+ .enqueue = (void *)qmap_enqueue,
+ .dequeue = (void *)qmap_dequeue,
+ .dispatch = (void *)qmap_dispatch,
+ .tick = (void *)qmap_tick,
+ .core_sched_before = (void *)qmap_core_sched_before,
+ .cpu_release = (void *)qmap_cpu_release,
+ .init_task = (void *)qmap_init_task,
+ .dump = (void *)qmap_dump,
+ .dump_cpu = (void *)qmap_dump_cpu,
+ .dump_task = (void *)qmap_dump_task,
+ .cpu_online = (void *)qmap_cpu_online,
+ .cpu_offline = (void *)qmap_cpu_offline,
+ .init = (void *)qmap_init,
+ .exit = (void *)qmap_exit,
+ .flags = SCX_OPS_ENQ_LAST,
+ .timeout_ms = 5000U,
+ .name = "qmap");
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
new file mode 100644
index 000000000000..ac45a02b4055
--- /dev/null
+++ b/tools/sched_ext/scx_qmap.c
@@ -0,0 +1,153 @@
+/* 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 <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <libgen.h>
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include "scx_qmap.bpf.skel.h"
+
+const char help_fmt[] =
+"A simple five-level FIFO queue sched_ext scheduler.\n"
+"\n"
+"See the top-level comment in .bpf.c for more details.\n"
+"\n"
+"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
+" [-P] [-d PID] [-D LEN] [-p] [-v]\n"
+"\n"
+" -s SLICE_US Override slice duration\n"
+" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n"
+" -t COUNT Stall every COUNT'th user thread\n"
+" -T COUNT Stall every COUNT'th kernel thread\n"
+" -l COUNT Trigger dispatch infinite looping after COUNT dispatches\n"
+" -b COUNT Dispatch upto COUNT tasks together\n"
+" -P Print out DSQ content to trace_pipe every second, use with -b\n"
+" -H Boost nice -20 tasks in SHARED_DSQ, use with -b\n"
+" -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n"
+" -D LEN Set scx_exit_info.dump buffer length\n"
+" -S Suppress qmap-specific debug dump\n"
+" -p Switch only tasks on SCHED_EXT policy instead of all\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 dummy)
+{
+ exit_req = 1;
+}
+
+int main(int argc, char **argv)
+{
+ struct scx_qmap *skel;
+ struct bpf_link *link;
+ int opt;
+
+ libbpf_set_print(libbpf_print_fn);
+ signal(SIGINT, sigint_handler);
+ signal(SIGTERM, sigint_handler);
+
+ skel = SCX_OPS_OPEN(qmap_ops, scx_qmap);
+
+ while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PHd:D:Spvh")) != -1) {
+ switch (opt) {
+ case 's':
+ skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
+ break;
+ case 'e':
+ skel->bss->test_error_cnt = strtoul(optarg, NULL, 0);
+ break;
+ case 't':
+ skel->rodata->stall_user_nth = strtoul(optarg, NULL, 0);
+ break;
+ case 'T':
+ skel->rodata->stall_kernel_nth = strtoul(optarg, NULL, 0);
+ break;
+ case 'l':
+ skel->rodata->dsp_inf_loop_after = strtoul(optarg, NULL, 0);
+ break;
+ case 'b':
+ skel->rodata->dsp_batch = strtoul(optarg, NULL, 0);
+ break;
+ case 'P':
+ skel->rodata->print_shared_dsq = true;
+ break;
+ case 'H':
+ skel->rodata->highpri_boosting = true;
+ break;
+ case 'd':
+ skel->rodata->disallow_tgid = strtol(optarg, NULL, 0);
+ if (skel->rodata->disallow_tgid < 0)
+ skel->rodata->disallow_tgid = getpid();
+ break;
+ case 'D':
+ skel->struct_ops.qmap_ops->exit_dump_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'S':
+ skel->rodata->suppress_dump = true;
+ break;
+ case 'p':
+ skel->struct_ops.qmap_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
+ break;
+ case 'v':
+ verbose = true;
+ break;
+ default:
+ fprintf(stderr, help_fmt, basename(argv[0]));
+ return opt != 'h';
+ }
+ }
+
+ SCX_OPS_LOAD(skel, qmap_ops, scx_qmap, uei);
+ link = SCX_OPS_ATTACH(skel, qmap_ops, scx_qmap);
+
+ while (!exit_req && !UEI_EXITED(skel, uei)) {
+ long nr_enqueued = skel->bss->nr_enqueued;
+ long nr_dispatched = skel->bss->nr_dispatched;
+
+ printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64" core=%"PRIu64" enq_ddsp=%"PRIu64"\n",
+ nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched,
+ skel->bss->nr_reenqueued, skel->bss->nr_dequeued,
+ skel->bss->nr_core_sched_execed,
+ skel->bss->nr_ddsp_from_enq);
+ printf(" exp_local=%"PRIu64" exp_remote=%"PRIu64" exp_timer=%"PRIu64" exp_lost=%"PRIu64"\n",
+ skel->bss->nr_expedited_local,
+ skel->bss->nr_expedited_remote,
+ skel->bss->nr_expedited_from_timer,
+ skel->bss->nr_expedited_lost);
+ if (__COMPAT_has_ksym("scx_bpf_cpuperf_cur"))
+ printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n",
+ skel->bss->cpuperf_min,
+ skel->bss->cpuperf_avg,
+ skel->bss->cpuperf_max,
+ skel->bss->cpuperf_target_min,
+ skel->bss->cpuperf_target_avg,
+ skel->bss->cpuperf_target_max);
+ fflush(stdout);
+ sleep(1);
+ }
+
+ bpf_link__destroy(link);
+ UEI_REPORT(skel, uei);
+ scx_qmap__destroy(skel);
+ /*
+ * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart
+ * on CPU hotplug events.
+ */
+ return 0;
+}
diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py
new file mode 100644
index 000000000000..8bc626ede1c4
--- /dev/null
+++ b/tools/sched_ext/scx_show_state.py
@@ -0,0 +1,40 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2024 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2024 Meta Platforms, Inc. and affiliates.
+
+desc = """
+This is a drgn script to show the current sched_ext state.
+For more info on drgn, visit https://github.com/osandov/drgn.
+"""
+
+import drgn
+import sys
+
+def err(s):
+ print(s, file=sys.stderr, flush=True)
+ sys.exit(1)
+
+def read_int(name):
+ return int(prog[name].value_())
+
+def read_atomic(name):
+ return prog[name].counter.value_()
+
+def read_static_key(name):
+ return prog[name].key.enabled.counter.value_()
+
+def ops_state_str(state):
+ return prog['scx_ops_enable_state_str'][state].string_().decode()
+
+ops = prog['scx_ops']
+enable_state = read_atomic("scx_ops_enable_state_var")
+
+print(f'ops : {ops.name.string_().decode()}')
+print(f'enabled : {read_static_key("__scx_ops_enabled")}')
+print(f'switching_all : {read_int("scx_switching_all")}')
+print(f'switched_all : {read_static_key("__scx_switched_all")}')
+print(f'enable_state : {ops_state_str(enable_state)} ({enable_state})')
+print(f'bypass_depth : {read_atomic("scx_ops_bypass_depth")}')
+print(f'nr_rejected : {read_atomic("scx_nr_rejected")}')
+print(f'enable_seq : {read_atomic("scx_enable_seq")}')
diff --git a/tools/sched_ext/scx_simple.bpf.c b/tools/sched_ext/scx_simple.bpf.c
new file mode 100644
index 000000000000..ed7e8d535fc5
--- /dev/null
+++ b/tools/sched_ext/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");
diff --git a/tools/sched_ext/scx_simple.c b/tools/sched_ext/scx_simple.c
new file mode 100644
index 000000000000..76d83199545c
--- /dev/null
+++ b/tools/sched_ext/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.bpf.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;
+}
diff --git a/tools/testing/selftests/sched_ext/.gitignore b/tools/testing/selftests/sched_ext/.gitignore
new file mode 100644
index 000000000000..ae5491a114c0
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/.gitignore
@@ -0,0 +1,6 @@
+*
+!*.c
+!*.h
+!Makefile
+!.gitignore
+!config
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
new file mode 100644
index 000000000000..0754a2c110a1
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -0,0 +1,218 @@
+# 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
+include ../lib.mk
+
+ifneq ($(LLVM),)
+ifneq ($(filter %/,$(LLVM)),)
+LLVM_PREFIX := $(LLVM)
+else ifneq ($(filter -%,$(LLVM)),)
+LLVM_SUFFIX := $(LLVM)
+endif
+
+CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+else
+CC := gcc
+endif # LLVM
+
+ifneq ($(CROSS_COMPILE),)
+$(error CROSS_COMPILE not supported for scx selftests)
+endif # CROSS_COMPILE
+
+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 := $(CURDIR)/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)/sbin/bpftool
+HOST_BUILD_DIR := $(OBJ_DIR)
+HOST_OUTPUT_DIR := $(OUTPUT_DIR)
+
+VMLINUX_BTF_PATHS ?= ../../../../vmlinux \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(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) -v -E - </dev/null 2>&1 \
+ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+endef
+
+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 \
+ $(call get_sys_includes,$(CLANG)) \
+ -Wall -Wno-compare-distinct-pointer-types \
+ -Wno-incompatible-function-pointer-types \
+ -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 \
+ $(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/ \
+ EXTRA_CFLAGS='-g -O0 -fPIC' \
+ DESTDIR=$(OUTPUT_DIR) prefix= all install_headers
+
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \
+ $(LIBBPF_OUTPUT) | $(OBJ_DIR)/bpftool
+ $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \
+ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \
+ EXTRA_CFLAGS='-g -O0' \
+ OUTPUT=$(OBJ_DIR)/bpftool/ \
+ LIBBPF_OUTPUT=$(OBJ_DIR)/libbpf/ \
+ LIBBPF_DESTDIR=$(OUTPUT_DIR)/ \
+ prefix= DESTDIR=$(OUTPUT_DIR)/ install-bin
+
+$(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 *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h
+ rm -f $(TEST_GEN_PROGS)
+ rm -f runner
+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 \
+ enq_last_no_enq_fails \
+ enq_select_cpu_fails \
+ ddsp_bogus_dsq_fail \
+ ddsp_vtimelocal_fail \
+ dsp_local_on \
+ exit \
+ hotplug \
+ init_enable_count \
+ maximal \
+ maybe_null \
+ minimal \
+ 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 \
+ test_example \
+
+testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets)))
+
+$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR)
+ $(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 $@ $(SCXOBJ_DIR)/runner.o
+
+$(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR)
+ $(CC) $(CFLAGS) -c $< -o $@
+
+runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets)
+ @echo "$(testcase-targets)"
+ $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS)
+
+TEST_GEN_PROGS := runner
+
+all: runner
+
+.PHONY: all clean help
+
+.DEFAULT_GOAL := all
+
+.DELETE_ON_ERROR:
+
+.SECONDARY:
diff --git a/tools/testing/selftests/sched_ext/config b/tools/testing/selftests/sched_ext/config
new file mode 100644
index 000000000000..0de9b4ee249d
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/config
@@ -0,0 +1,9 @@
+CONFIG_SCHED_DEBUG=y
+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
diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c
new file mode 100644
index 000000000000..23f79ed343f0
--- /dev/null
+++ b/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 = create_dsq_init_task,
+ .exit_task = create_dsq_exit_task,
+ .init = create_dsq_init,
+ .name = "create_dsq",
+};
diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c
new file mode 100644
index 000000000000..fa946d9146d4
--- /dev/null
+++ b/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_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+ *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)
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
new file mode 100644
index 000000000000..e97ad41d354a
--- /dev/null
+++ b/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_dispatch_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 = ddsp_bogus_dsq_fail_select_cpu,
+ .exit = ddsp_bogus_dsq_fail_exit,
+ .name = "ddsp_bogus_dsq_fail",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c
new file mode 100644
index 000000000000..e65d22f23f3b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.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>
+ * 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
new file mode 100644
index 000000000000..dde7e7dafbfb
--- /dev/null
+++ b/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_dispatch_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 = ddsp_vtimelocal_fail_select_cpu,
+ .exit = ddsp_vtimelocal_fail_exit,
+ .name = "ddsp_vtimelocal_fail",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
new file mode 100644
index 000000000000..abafee587cd6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c
@@ -0,0 +1,56 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
new file mode 100644
index 000000000000..efb4672decb4
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -0,0 +1,65 @@
+/* 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;
+
+ target = bpf_get_prandom_u32() % nr_cpus;
+
+ scx_bpf_dispatch(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 = dsp_local_on_select_cpu,
+ .enqueue = dsp_local_on_enqueue,
+ .dispatch = dsp_local_on_dispatch,
+ .exit = dsp_local_on_exit,
+ .name = "dsp_local_on",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c
new file mode 100644
index 000000000000..472851b56854
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.c
@@ -0,0 +1,58 @@
+/* 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");
+
+ 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);
+
+ 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 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 osp.dispatch()",
+ .setup = setup,
+ .run = run,
+ .cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&dsp_local_on)
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
new file mode 100644
index 000000000000..b0b99531d5d5
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c
@@ -0,0 +1,21 @@
+/* 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";
+
+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,
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
new file mode 100644
index 000000000000..2a3eda5e2c0b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c
@@ -0,0 +1,60 @@
+/* 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_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+ *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 succeeded in to attaching scheduler");
+ 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 fail to load 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)
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
new file mode 100644
index 000000000000..b3dfc1033cd6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -0,0 +1,43 @@
+/* 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";
+
+/* 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(enq_select_cpu_fails_select_cpu, struct task_struct *p,
+ s32 prev_cpu, u64 wake_flags)
+{
+ return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
+ u64 enq_flags)
+{
+ /*
+ * Need to initialize the variable or the verifier will fail to load.
+ * Improving these semantics is actively being worked on.
+ */
+ bool found = false;
+
+ /* Can only call from ops.select_cpu() */
+ scx_bpf_select_cpu_dfl(p, 0, 0, &found);
+
+ scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_select_cpu_fails_ops = {
+ .select_cpu = enq_select_cpu_fails_select_cpu,
+ .enqueue = enq_select_cpu_fails_enqueue,
+ .name = "enq_select_cpu_fails",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
new file mode 100644
index 000000000000..dd1350e5f002
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c
@@ -0,0 +1,61 @@
+/* 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_fails.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+ struct enq_select_cpu_fails *skel;
+
+ skel = enq_select_cpu_fails__open_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+ *ctx = skel;
+
+ return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+ struct enq_select_cpu_fails *skel = ctx;
+ struct bpf_link *link;
+
+ link = bpf_map__attach_struct_ops(skel->maps.enq_select_cpu_fails_ops);
+ if (!link) {
+ SCX_ERR("Failed to attach scheduler");
+ return SCX_TEST_FAIL;
+ }
+
+ sleep(1);
+
+ bpf_link__destroy(link);
+
+ return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+ struct enq_select_cpu_fails *skel = ctx;
+
+ enq_select_cpu_fails__destroy(skel);
+}
+
+struct scx_test enq_select_cpu_fails = {
+ .name = "enq_select_cpu_fails",
+ .description = "Verify we fail to call scx_bpf_select_cpu_dfl() "
+ "from ops.enqueue()",
+ .setup = setup,
+ .run = run,
+ .cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&enq_select_cpu_fails)
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
new file mode 100644
index 000000000000..ae12ddaac921
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -0,0 +1,84 @@
+/* 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)
+
+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_dispatch(p, SCX_DSQ_GLOBAL, 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_consume(SCX_DSQ_GLOBAL);
+}
+
+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 0;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops exit_ops = {
+ .select_cpu = exit_select_cpu,
+ .enqueue = exit_enqueue,
+ .dispatch = exit_dispatch,
+ .init_task = exit_init_task,
+ .enable = exit_enable,
+ .exit = exit_exit,
+ .init = exit_init,
+ .name = "exit",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c
new file mode 100644
index 000000000000..31bcd06e21cd
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/exit.c
@@ -0,0 +1,55 @@
+/* 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];
+
+ skel = exit__open();
+ skel->rodata->exit_point = tc;
+ exit__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)
diff --git a/tools/testing/selftests/sched_ext/exit_test.h b/tools/testing/selftests/sched_ext/exit_test.h
new file mode 100644
index 000000000000..94f0268b9cb8
--- /dev/null
+++ b/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__
diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c
new file mode 100644
index 000000000000..8f2601db39f3
--- /dev/null
+++ b/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 = hotplug_cpu_online,
+ .cpu_offline = hotplug_cpu_offline,
+ .exit = hotplug_exit,
+ .name = "hotplug_cbs",
+ .timeout_ms = 1000U,
+};
+
+SEC(".struct_ops.link")
+struct sched_ext_ops hotplug_nocb_ops = {
+ .exit = hotplug_exit,
+ .name = "hotplug_nocbs",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c
new file mode 100644
index 000000000000..87bf220b1bce
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/hotplug.c
@@ -0,0 +1,168 @@
+/* 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 <sched.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_and_load();
+ SCX_ASSERT(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)
diff --git a/tools/testing/selftests/sched_ext/hotplug_test.h b/tools/testing/selftests/sched_ext/hotplug_test.h
new file mode 100644
index 000000000000..73d236f90787
--- /dev/null
+++ b/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__
diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c
new file mode 100644
index 000000000000..47ea89a626c3
--- /dev/null
+++ b/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 = cnt_init_task,
+ .exit_task = cnt_exit_task,
+ .enable = cnt_enable,
+ .disable = cnt_disable,
+ .name = "init_enable_count",
+};
diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c
new file mode 100644
index 000000000000..97d45f1e5597
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/init_enable_count.c
@@ -0,0 +1,166 @@
+/* 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 <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 struct init_enable_count *
+open_load_prog(bool global)
+{
+ struct init_enable_count *skel;
+
+ skel = init_enable_count__open();
+ SCX_BUG_ON(!skel, "Failed to open skel");
+
+ if (!global)
+ skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL;
+
+ SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel");
+
+ return skel;
+}
+
+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];
+
+ skel = open_load_prog(global);
+
+ /*
+ * 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.
+ */
+ for (i = 0; i < num_pre_forks; i++) {
+ pids[i] = fork();
+ SCX_FAIL_IF(pids[i] < 0, "Failed to fork child");
+ if (pids[i] == 0) {
+ sleep(1);
+ exit(0);
+ }
+ }
+
+ link = bpf_map__attach_struct_ops(skel->maps.init_enable_count_ops);
+ SCX_FAIL_IF(!link, "Failed to attach struct_ops");
+
+ for (i = 0; i < num_pre_forks; i++) {
+ SCX_FAIL_IF(waitpid(pids[i], &status, 0) != pids[i],
+ "Failed to wait for pre-forked child\n");
+
+ SCX_FAIL_IF(status != 0, "Pre-forked child %d exited with status %d\n", i,
+ status);
+ }
+
+ 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 do the correct amount of counting of init, "
+ "enable, etc callbacks.",
+ .run = run,
+};
+REGISTER_SCX_TEST(&init_enable_count)
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
new file mode 100644
index 000000000000..00bfa9cb95d3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -0,0 +1,164 @@
+/* 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";
+
+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_dispatch(p, SCX_DSQ_GLOBAL, 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_consume(SCX_DSQ_GLOBAL);
+}
+
+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)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_acquire, s32 cpu,
+ struct scx_cpu_acquire_args *args)
+{}
+
+void BPF_STRUCT_OPS(maximal_cpu_release, s32 cpu,
+ struct scx_cpu_release_args *args)
+{}
+
+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)
+{}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
+{
+ return 0;
+}
+
+void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
+{}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops maximal_ops = {
+ .select_cpu = maximal_select_cpu,
+ .enqueue = maximal_enqueue,
+ .dequeue = maximal_dequeue,
+ .dispatch = maximal_dispatch,
+ .runnable = maximal_runnable,
+ .running = maximal_running,
+ .stopping = maximal_stopping,
+ .quiescent = maximal_quiescent,
+ .yield = maximal_yield,
+ .core_sched_before = maximal_core_sched_before,
+ .set_weight = maximal_set_weight,
+ .set_cpumask = maximal_set_cpumask,
+ .update_idle = maximal_update_idle,
+ .cpu_acquire = maximal_cpu_acquire,
+ .cpu_release = maximal_cpu_release,
+ .cpu_online = maximal_cpu_online,
+ .cpu_offline = maximal_cpu_offline,
+ .init_task = maximal_init_task,
+ .enable = maximal_enable,
+ .exit_task = maximal_exit_task,
+ .disable = maximal_disable,
+ .cgroup_init = maximal_cgroup_init,
+ .cgroup_exit = maximal_cgroup_exit,
+ .cgroup_prep_move = maximal_cgroup_prep_move,
+ .cgroup_move = maximal_cgroup_move,
+ .cgroup_cancel_move = maximal_cgroup_cancel_move,
+ .cgroup_set_weight = maximal_cgroup_set_weight,
+ .init = maximal_init,
+ .exit = maximal_exit,
+ .name = "maximal",
+};
diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c
new file mode 100644
index 000000000000..f38fc973c380
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/maximal.c
@@ -0,0 +1,51 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and load 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)
diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c
new file mode 100644
index 000000000000..27d0f386acfb
--- /dev/null
+++ b/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 = maybe_null_success_dispatch,
+ .yield = maybe_null_success_yield,
+ .enable = maybe_null_running,
+ .name = "minimal",
+};
diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c
new file mode 100644
index 000000000000..31cfafb0cf65
--- /dev/null
+++ b/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 work for .dispatch",
+ .run = run,
+};
+REGISTER_SCX_TEST(&maybe_null)
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c
new file mode 100644
index 000000000000..c0641050271d
--- /dev/null
+++ b/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 = maybe_null_fail_dispatch,
+ .enable = maybe_null_running,
+ .name = "maybe_null_fail_dispatch",
+};
diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c
new file mode 100644
index 000000000000..3c1740028e3b
--- /dev/null
+++ b/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 = maybe_null_fail_yield,
+ .enable = maybe_null_running,
+ .name = "maybe_null_fail_yield",
+};
diff --git a/tools/testing/selftests/sched_ext/minimal.bpf.c b/tools/testing/selftests/sched_ext/minimal.bpf.c
new file mode 100644
index 000000000000..6a7eccef0104
--- /dev/null
+++ b/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",
+};
diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c
new file mode 100644
index 000000000000..6c5db8ebbf8a
--- /dev/null
+++ b/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_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+ *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)
diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c
new file mode 100644
index 000000000000..6a4d7c48e3f2
--- /dev/null
+++ b/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 = prog_run_exit,
+ .name = "prog_run",
+};
diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c
new file mode 100644
index 000000000000..3cd57ef8daaa
--- /dev/null
+++ b/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_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+ *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)
diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c
new file mode 100644
index 000000000000..5cfba2d6e056
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/reload_loop.c
@@ -0,0 +1,75 @@
+/* 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_and_load();
+ if (!skel) {
+ SCX_ERR("Failed to open and load skel");
+ return SCX_TEST_FAIL;
+ }
+
+ 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)
diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c
new file mode 100644
index 000000000000..eab48c7ff309
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/runner.c
@@ -0,0 +1,201 @@
+/* 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] [-h]\n"
+"\n"
+" -t TEST Only run tests whose name includes this string\n"
+" -s Include print output for skipped 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;
+
+#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");
+}
+
+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;
+ 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, "qst:h")) != -1) {
+ switch (opt) {
+ case 'q':
+ quiet = true;
+ break;
+ case 's':
+ print_skipped = true;
+ break;
+ case 't':
+ filter = optarg;
+ break;
+ default:
+ fprintf(stderr, help_fmt, basename(argv[0]));
+ return opt != 'h';
+ }
+ }
+
+ for (i = 0; i < __scx_num_tests; i++) {
+ enum scx_test_status status;
+ struct scx_test *test = &__scx_tests[i];
+
+ 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++;
+ break;
+ case SCX_TEST_FAIL:
+ failed++;
+ 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);
+
+ return 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;
+}
diff --git a/tools/testing/selftests/sched_ext/scx_test.h b/tools/testing/selftests/sched_ext/scx_test.h
new file mode 100644
index 000000000000..90b8d6915bb7
--- /dev/null
+++ b/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__
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
new file mode 100644
index 000000000000..2ed2991afafe
--- /dev/null
+++ b/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_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dfl_ops = {
+ .enqueue = select_cpu_dfl_enqueue,
+ .name = "select_cpu_dfl",
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c
new file mode 100644
index 000000000000..a53a40c2d2f0
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c
@@ -0,0 +1,72 @@
+/* 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.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_CHILDREN 1028
+
+static enum scx_test_status setup(void **ctx)
+{
+ struct select_cpu_dfl *skel;
+
+ skel = select_cpu_dfl__open_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and load skel");
+ *ctx = skel;
+
+ return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+ struct select_cpu_dfl *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_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 *skel = ctx;
+
+ select_cpu_dfl__destroy(skel);
+}
+
+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)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
new file mode 100644
index 000000000000..4bb5abb2d369
--- /dev/null
+++ b/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_dispatch(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 = select_cpu_dfl_nodispatch_select_cpu,
+ .enqueue = select_cpu_dfl_nodispatch_enqueue,
+ .init_task = select_cpu_dfl_nodispatch_init_task,
+ .name = "select_cpu_dfl_nodispatch",
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
new file mode 100644
index 000000000000..1d85bf4bf3a3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c
@@ -0,0 +1,72 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
new file mode 100644
index 000000000000..f0b96a4a04b2
--- /dev/null
+++ b/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_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
+ return cpu;
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops select_cpu_dispatch_ops = {
+ .select_cpu = select_cpu_dispatch_select_cpu,
+ .name = "select_cpu_dispatch",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c
new file mode 100644
index 000000000000..0309ca8785b3
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c
@@ -0,0 +1,70 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
new file mode 100644
index 000000000000..7b42ddce0f56
--- /dev/null
+++ b/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_dispatch(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 = select_cpu_dispatch_bad_dsq_select_cpu,
+ .exit = select_cpu_dispatch_bad_dsq_exit,
+ .name = "select_cpu_dispatch_bad_dsq",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
new file mode 100644
index 000000000000..47eb6ed7627d
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c
@@ -0,0 +1,56 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
new file mode 100644
index 000000000000..653e3dc0b4dc
--- /dev/null
+++ b/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_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+ scx_bpf_dispatch(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 = select_cpu_dispatch_dbl_dsp_select_cpu,
+ .exit = select_cpu_dispatch_dbl_dsp_exit,
+ .name = "select_cpu_dispatch_dbl_dsp",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
new file mode 100644
index 000000000000..48ff028a3c46
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c
@@ -0,0 +1,56 @@
+/* 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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
new file mode 100644
index 000000000000..7f3ebf4fc2ea
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -0,0 +1,92 @@
+/* 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_dispatch_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_dispatch_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_consume(VTIME_DSQ))
+ 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)
+{
+ p->scx.dsq_vtime += (SCX_SLICE_DFL - p->scx.slice) * 100 / p->scx.weight;
+}
+
+void BPF_STRUCT_OPS(select_cpu_vtime_enable, struct task_struct *p)
+{
+ p->scx.dsq_vtime = 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 = select_cpu_vtime_select_cpu,
+ .dispatch = select_cpu_vtime_dispatch,
+ .running = select_cpu_vtime_running,
+ .stopping = select_cpu_vtime_stopping,
+ .enable = select_cpu_vtime_enable,
+ .init = select_cpu_vtime_init,
+ .name = "select_cpu_vtime",
+ .timeout_ms = 1000U,
+};
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c
new file mode 100644
index 000000000000..b4629c2364f5
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.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 <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_and_load();
+ SCX_FAIL_IF(!skel, "Failed to open and 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)
diff --git a/tools/testing/selftests/sched_ext/test_example.c b/tools/testing/selftests/sched_ext/test_example.c
new file mode 100644
index 000000000000..ce36cdf03cdc
--- /dev/null
+++ b/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)
diff --git a/tools/testing/selftests/sched_ext/util.c b/tools/testing/selftests/sched_ext/util.c
new file mode 100644
index 000000000000..e47769c91918
--- /dev/null
+++ b/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, "%lu", val);
+ if (ret < 0)
+ return ret;
+
+ if (write_text(path, buf, sizeof(buf)) <= 0)
+ return -1;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/sched_ext/util.h b/tools/testing/selftests/sched_ext/util.h
new file mode 100644
index 000000000000..bc13dfec1267
--- /dev/null
+++ b/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_H__
--
2.47.0.rc0
Reference in New Issue View Git Blame Copy Permalink