Files
linux/tools/sched_ext/scx_cpu0.bpf.c
Tejun Heo 860683763e sched_ext: Add enq_flags to scx_bpf_dsq_move_to_local()
scx_bpf_dsq_move_to_local() moves a task from a non-local DSQ to the
current CPU's local DSQ. This is an indirect way of dispatching to a local
DSQ and should support enq_flags like direct dispatches do - e.g.
SCX_ENQ_HEAD for head-of-queue insertion and SCX_ENQ_IMMED for immediate
execution guarantees.

Add scx_bpf_dsq_move_to_local___v2() with an enq_flags parameter. The
original becomes a v1 compat wrapper passing 0. The compat macro is updated
to a three-level chain: v2 (7.1+) -> v1 (current) -> scx_bpf_consume
(pre-rename). All in-tree BPF schedulers are updated to pass 0.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
2026-03-13 09:43:23 -10:00

97 lines
2.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* A CPU0 scheduler.
*
* This scheduler queues all tasks to a shared DSQ and only dispatches them on
* CPU0 in FIFO order. This is useful for testing bypass behavior when many
* tasks are concentrated on a single CPU. If the load balancer doesn't work,
* bypass mode can trigger task hangs or RCU stalls as the queue is long and
* there's only one CPU working on it.
*
* - Statistics tracking how many tasks are queued to local and CPU0 DSQs.
* - Termination notification for userspace.
*
* Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
* Copyright (c) 2025 Tejun Heo <tj@kernel.org>
*/
#include <scx/common.bpf.h>
char _license[] SEC("license") = "GPL";
const volatile u32 nr_cpus = 32; /* !0 for veristat, set during init */
UEI_DEFINE(uei);
/*
* We create a custom DSQ with ID 0 that we dispatch to and consume from on
* CPU0.
*/
#define DSQ_CPU0 0
struct {
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
__uint(key_size, sizeof(u32));
__uint(value_size, sizeof(u64));
__uint(max_entries, 2); /* [local, cpu0] */
} stats SEC(".maps");
static void stat_inc(u32 idx)
{
u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx);
if (cnt_p)
(*cnt_p)++;
}
s32 BPF_STRUCT_OPS(cpu0_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
{
return 0;
}
void BPF_STRUCT_OPS(cpu0_enqueue, struct task_struct *p, u64 enq_flags)
{
/*
* select_cpu() always picks CPU0. If @p is not on CPU0, it can't run on
* CPU 0. Queue on whichever CPU it's currently only.
*/
if (scx_bpf_task_cpu(p) != 0) {
stat_inc(0); /* count local queueing */
scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
return;
}
stat_inc(1); /* count cpu0 queueing */
scx_bpf_dsq_insert(p, DSQ_CPU0, SCX_SLICE_DFL, enq_flags);
}
void BPF_STRUCT_OPS(cpu0_dispatch, s32 cpu, struct task_struct *prev)
{
if (cpu == 0)
scx_bpf_dsq_move_to_local(DSQ_CPU0, 0);
}
s32 BPF_STRUCT_OPS_SLEEPABLE(cpu0_init)
{
int ret;
ret = scx_bpf_create_dsq(DSQ_CPU0, -1);
if (ret) {
scx_bpf_error("failed to create DSQ %d (%d)", DSQ_CPU0, ret);
return ret;
}
return 0;
}
void BPF_STRUCT_OPS(cpu0_exit, struct scx_exit_info *ei)
{
UEI_RECORD(uei, ei);
}
SCX_OPS_DEFINE(cpu0_ops,
.select_cpu = (void *)cpu0_select_cpu,
.enqueue = (void *)cpu0_enqueue,
.dispatch = (void *)cpu0_dispatch,
.init = (void *)cpu0_init,
.exit = (void *)cpu0_exit,
.name = "cpu0");