e9fe182772
dsp_local_on has several incorrect assumptions, one of which is that p->nr_cpus_allowed always tracks p->cpus_ptr. This is not true when a task is scheduled out while migration is disabled - p->cpus_ptr is temporarily overridden to the previous CPU while p->nr_cpus_allowed remains unchanged. This led to sporadic test faliures when dsp_local_on_dispatch() tries to put a migration disabled task to a different CPU. Fix it by keeping the previous CPU when migration is disabled. There are SCX schedulers that make use of p->nr_cpus_allowed. They should also implement explicit handling for p->migration_disabled. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Ihor Solodrai <ihor.solodrai@pm.me> Cc: Andrea Righi <arighi@nvidia.com> Cc: Changwoo Min <changwoo@igalia.com>
68 lines
1.5 KiB
C
68 lines
1.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
|
|
* Copyright (c) 2024 David Vernet <dvernet@meta.com>
|
|
*/
|
|
#include <scx/common.bpf.h>
|
|
|
|
char _license[] SEC("license") = "GPL";
|
|
const volatile s32 nr_cpus;
|
|
|
|
UEI_DEFINE(uei);
|
|
|
|
struct {
|
|
__uint(type, BPF_MAP_TYPE_QUEUE);
|
|
__uint(max_entries, 8192);
|
|
__type(value, s32);
|
|
} queue SEC(".maps");
|
|
|
|
s32 BPF_STRUCT_OPS(dsp_local_on_select_cpu, struct task_struct *p,
|
|
s32 prev_cpu, u64 wake_flags)
|
|
{
|
|
return prev_cpu;
|
|
}
|
|
|
|
void BPF_STRUCT_OPS(dsp_local_on_enqueue, struct task_struct *p,
|
|
u64 enq_flags)
|
|
{
|
|
s32 pid = p->pid;
|
|
|
|
if (bpf_map_push_elem(&queue, &pid, 0))
|
|
scx_bpf_error("Failed to enqueue %s[%d]", p->comm, p->pid);
|
|
}
|
|
|
|
void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
|
|
{
|
|
s32 pid, target;
|
|
struct task_struct *p;
|
|
|
|
if (bpf_map_pop_elem(&queue, &pid))
|
|
return;
|
|
|
|
p = bpf_task_from_pid(pid);
|
|
if (!p)
|
|
return;
|
|
|
|
if (p->nr_cpus_allowed == nr_cpus && !p->migration_disabled)
|
|
target = bpf_get_prandom_u32() % nr_cpus;
|
|
else
|
|
target = scx_bpf_task_cpu(p);
|
|
|
|
scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
|
|
bpf_task_release(p);
|
|
}
|
|
|
|
void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei)
|
|
{
|
|
UEI_RECORD(uei, ei);
|
|
}
|
|
|
|
SEC(".struct_ops.link")
|
|
struct sched_ext_ops dsp_local_on_ops = {
|
|
.select_cpu = (void *) dsp_local_on_select_cpu,
|
|
.enqueue = (void *) dsp_local_on_enqueue,
|
|
.dispatch = (void *) dsp_local_on_dispatch,
|
|
.exit = (void *) dsp_local_on_exit,
|
|
.name = "dsp_local_on",
|
|
.timeout_ms = 1000U,
|
|
};
|