@@ -1204,7 +1204,7 @@ bool sched_can_stop_tick(struct rq *rq)
* if there's more than one we need the tick for involuntary
* preemption.
*/
- if (rq->nr_running > 1)
+ if (!scx_switched_all() && rq->nr_running > 1)
return false;
return true;
@@ -5590,8 +5590,10 @@ void scheduler_tick(void)
perf_event_task_tick();
#ifdef CONFIG_SMP
- rq->idle_balance = idle_cpu(cpu);
- trigger_load_balance(rq);
+ if (!scx_switched_all()) {
+ rq->idle_balance = idle_cpu(cpu);
+ trigger_load_balance(rq);
+ }
#endif
}
@@ -73,6 +73,10 @@ 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 bool scx_switch_all_req;
+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;
@@ -1966,6 +1970,8 @@ bool task_on_scx(struct task_struct *p)
{
if (!scx_enabled() || scx_ops_disabling())
return false;
+ if (READ_ONCE(scx_switching_all))
+ return true;
return p->policy == SCHED_EXT;
}
@@ -2092,6 +2098,9 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
*/
mutex_lock(&scx_ops_enable_mutex);
+ static_branch_disable(&__scx_switched_all);
+ WRITE_ONCE(scx_switching_all, false);
+
/* avoid racing against fork */
cpus_read_lock();
percpu_down_write(&scx_fork_rwsem);
@@ -2276,6 +2285,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops)
*/
cpus_read_lock();
+ scx_switch_all_req = false;
if (scx_ops.init) {
ret = SCX_CALL_OP_RET(SCX_KF_INIT | SCX_KF_SLEEPABLE, init);
if (ret) {
@@ -2391,6 +2401,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops)
* transitions here are synchronized against sched_ext_free() through
* scx_tasks_lock.
*/
+ WRITE_ONCE(scx_switching_all, scx_switch_all_req);
+
scx_task_iter_init(&sti);
while ((p = scx_task_iter_next_filtered_locked(&sti))) {
if (READ_ONCE(p->__state) != TASK_DEAD) {
@@ -2422,6 +2434,9 @@ static int scx_ops_enable(struct sched_ext_ops *ops)
goto err_disable_unlock;
}
+ if (scx_switch_all_req)
+ static_branch_enable_cpuslocked(&__scx_switched_all);
+
cpus_read_unlock();
mutex_unlock(&scx_ops_enable_mutex);
@@ -2456,6 +2471,9 @@ static int scx_debug_show(struct seq_file *m, void *v)
mutex_lock(&scx_ops_enable_mutex);
seq_printf(m, "%-30s: %s\n", "ops", scx_ops.name);
seq_printf(m, "%-30s: %ld\n", "enabled", scx_enabled());
+ seq_printf(m, "%-30s: %d\n", "switching_all",
+ READ_ONCE(scx_switching_all));
+ seq_printf(m, "%-30s: %ld\n", "switched_all", scx_switched_all());
seq_printf(m, "%-30s: %s\n", "enable_state",
scx_ops_enable_state_str[scx_ops_enable_state()]);
seq_printf(m, "%-30s: %llu\n", "nr_rejected",
@@ -2694,6 +2712,31 @@ __diag_push();
__diag_ignore_all("-Wmissing-prototypes",
"Global functions as their definitions will be in vmlinux BTF");
+/**
+ * scx_bpf_switch_all - Switch all tasks into SCX
+ * @into_scx: switch direction
+ *
+ * If @into_scx is %true, all existing and future non-dl/rt tasks are switched
+ * to SCX. If %false, only tasks which have %SCHED_EXT explicitly set are put on
+ * SCX. The actual switching is asynchronous. Can be called from ops.init().
+ */
+void scx_bpf_switch_all(void)
+{
+ if (!scx_kf_allowed(SCX_KF_INIT))
+ return;
+
+ scx_switch_all_req = true;
+}
+
+BTF_SET8_START(scx_kfunc_ids_init)
+BTF_ID_FLAGS(func, scx_bpf_switch_all)
+BTF_SET8_END(scx_kfunc_ids_init)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_init = {
+ .owner = THIS_MODULE,
+ .set = &scx_kfunc_ids_init,
+};
+
/**
* scx_bpf_create_dsq - Create a custom DSQ
* @dsq_id: DSQ to create
@@ -3131,6 +3174,8 @@ static int __init register_ext_kfuncs(void)
* check using scx_kf_allowed().
*/
if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+ &scx_kfunc_set_init)) ||
+ (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
&scx_kfunc_set_sleepable)) ||
(ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
&scx_kfunc_set_enqueue_dispatch)) ||
@@ -60,7 +60,9 @@ extern unsigned long scx_watchdog_timeout;
extern unsigned long scx_watchdog_timestamp;
DECLARE_STATIC_KEY_FALSE(__scx_ops_enabled);
+DECLARE_STATIC_KEY_FALSE(__scx_switched_all);
#define scx_enabled() static_branch_unlikely(&__scx_ops_enabled)
+#define scx_switched_all() static_branch_unlikely(&__scx_switched_all)
bool task_on_scx(struct task_struct *p);
void scx_pre_fork(struct task_struct *p);
@@ -95,6 +97,8 @@ static inline void scx_notify_sched_tick(void)
static inline const struct sched_class *next_active_class(const struct sched_class *class)
{
class++;
+ if (scx_switched_all() && class == &fair_sched_class)
+ class++;
if (!scx_enabled() && class == &ext_sched_class)
class++;
return class;
@@ -117,6 +121,7 @@ static inline const struct sched_class *next_active_class(const struct sched_cla
#else /* CONFIG_SCHED_CLASS_EXT */
#define scx_enabled() false
+#define scx_switched_all() false
static inline void scx_pre_fork(struct task_struct *p) {}
static inline int scx_fork(struct task_struct *p) { return 0; }
@@ -66,6 +66,7 @@ bool bpf_cpumask_and(struct bpf_cpumask *dst, const struct cpumask *src1,
const struct cpumask *src2) __ksym;
u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym;
+void scx_bpf_switch_all(void) __ksym;
s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym;
bool scx_bpf_consume(u64 dsq_id) __ksym;
u32 scx_bpf_dispatch_nr_slots(void) __ksym;
@@ -7,6 +7,7 @@
*
* - Statistics tracking how many are queued to local and global dsq's.
* - Termination notification for userspace.
+ * - Support for switch_all.
*
* Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
* Copyright (c) 2022 Tejun Heo <tj@kernel.org>
@@ -16,6 +17,8 @@
char _license[] SEC("license") = "GPL";
+const volatile bool switch_all;
+
struct user_exit_info uei;
struct {
@@ -32,6 +35,13 @@ static void stat_inc(u32 idx)
(*cnt_p)++;
}
+s32 BPF_STRUCT_OPS(dummy_init)
+{
+ if (switch_all)
+ scx_bpf_switch_all();
+ return 0;
+}
+
void BPF_STRUCT_OPS(dummy_enqueue, struct task_struct *p, u64 enq_flags)
{
if (enq_flags & SCX_ENQ_LOCAL) {
@@ -51,6 +61,7 @@ void BPF_STRUCT_OPS(dummy_exit, struct scx_exit_info *ei)
SEC(".struct_ops")
struct sched_ext_ops dummy_ops = {
.enqueue = (void *)dummy_enqueue,
+ .init = (void *)dummy_init,
.exit = (void *)dummy_exit,
.name = "dummy",
};
@@ -19,8 +19,9 @@ const char help_fmt[] =
"\n"
"See the top-level comment in .bpf.c for more details.\n"
"\n"
-"Usage: %s\n"
+"Usage: %s [-a]\n"
"\n"
+" -a Switch all tasks\n"
" -h Display this help and exit\n";
static volatile int exit_req;
@@ -64,8 +65,11 @@ int main(int argc, char **argv)
skel = scx_example_dummy__open();
assert(skel);
- while ((opt = getopt(argc, argv, "h")) != -1) {
+ while ((opt = getopt(argc, argv, "ah")) != -1) {
switch (opt) {
+ case 'a':
+ skel->rodata->switch_all = true;
+ break;
default:
fprintf(stderr, help_fmt, basename(argv[0]));
return opt != 'h';
@@ -22,6 +22,7 @@
char _license[] SEC("license") = "GPL";
const volatile u64 slice_ns = SCX_SLICE_DFL;
+const volatile bool switch_all;
const volatile u32 stall_user_nth;
const volatile u32 stall_kernel_nth;
const volatile s32 disallow_tgid;
@@ -236,6 +237,13 @@ s32 BPF_STRUCT_OPS(qmap_prep_enable, struct task_struct *p,
return -ENOMEM;
}
+s32 BPF_STRUCT_OPS(qmap_init)
+{
+ if (switch_all)
+ scx_bpf_switch_all();
+ return 0;
+}
+
void BPF_STRUCT_OPS(qmap_exit, struct scx_exit_info *ei)
{
uei_record(&uei, ei);
@@ -248,6 +256,7 @@ struct sched_ext_ops qmap_ops = {
.dequeue = (void *)qmap_dequeue,
.dispatch = (void *)qmap_dispatch,
.prep_enable = (void *)qmap_prep_enable,
+ .init = (void *)qmap_init,
.exit = (void *)qmap_exit,
.timeout_ms = 5000U,
.name = "qmap",
@@ -20,7 +20,7 @@ const char help_fmt[] =
"\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] [-d PID]\n"
+"Usage: %s [-a] [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-d PID]\n"
"\n"
" -s SLICE_US Override slice duration\n"
" -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n"
@@ -50,8 +50,11 @@ int main(int argc, char **argv)
skel = scx_example_qmap__open();
assert(skel);
- while ((opt = getopt(argc, argv, "hs:e:t:T:d:")) != -1) {
+ while ((opt = getopt(argc, argv, "ahs:e:t:T:d:")) != -1) {
switch (opt) {
+ case 'a':
+ skel->rodata->switch_all = true;
+ break;
case 's':
skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
break;