sched_ext: Fix incorrect sched_class settings for per-cpu migration tasks

When loading the ebpf scheduler, the tasks in the scx_tasks list will
be traversed and invoke __setscheduler_class() to get new sched_class.
however, this would also incorrectly set the per-cpu migration
task's->sched_class to rt_sched_class, even after unload, the per-cpu
migration task's->sched_class remains sched_rt_class.

The log for this issue is as follows:

./scx_rustland --stats 1
[  199.245639][  T630] sched_ext: "rustland" does not implement cgroup cpu.weight
[  199.269213][  T630] sched_ext: BPF scheduler "rustland" enabled
04:25:09 [INFO] RustLand scheduler attached

bpftrace -e 'iter:task /strcontains(ctx->task->comm, "migration")/
{ printf("%s:%d->%pS\n", ctx->task->comm, ctx->task->pid, ctx->task->sched_class); }'
Attaching 1 probe...
migration/0:24->rt_sched_class+0x0/0xe0
migration/1:27->rt_sched_class+0x0/0xe0
migration/2:33->rt_sched_class+0x0/0xe0
migration/3:39->rt_sched_class+0x0/0xe0
migration/4:45->rt_sched_class+0x0/0xe0
migration/5:52->rt_sched_class+0x0/0xe0
migration/6:58->rt_sched_class+0x0/0xe0
migration/7:64->rt_sched_class+0x0/0xe0

sched_ext: BPF scheduler "rustland" disabled (unregistered from user space)
EXIT: unregistered from user space
04:25:21 [INFO] Unregister RustLand scheduler

bpftrace -e 'iter:task /strcontains(ctx->task->comm, "migration")/
{ printf("%s:%d->%pS\n", ctx->task->comm, ctx->task->pid, ctx->task->sched_class); }'
Attaching 1 probe...
migration/0:24->rt_sched_class+0x0/0xe0
migration/1:27->rt_sched_class+0x0/0xe0
migration/2:33->rt_sched_class+0x0/0xe0
migration/3:39->rt_sched_class+0x0/0xe0
migration/4:45->rt_sched_class+0x0/0xe0
migration/5:52->rt_sched_class+0x0/0xe0
migration/6:58->rt_sched_class+0x0/0xe0
migration/7:64->rt_sched_class+0x0/0xe0

This commit therefore generate a new scx_setscheduler_class() and
add check for stop_sched_class to replace __setscheduler_class().

Fixes: f0e1a0643a59 ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Zqiang <qiang.zhang@linux.dev>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index dca9ca0c185411a15a23901a9cebd9cfa78d984b..b563b8c3fd24d1d2d6ef181da0ee430fec0462a5 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -248,6 +248,14 @@ static struct scx_dispatch_q *find_user_dsq(struct scx_sched *sch, u64 dsq_id)
        return rhashtable_lookup(&sch->dsq_hash, &dsq_id, dsq_hash_params);
 }
 
+static const struct sched_class *scx_setscheduler_class(struct task_struct *p)
+{
+       if (p->sched_class == &stop_sched_class)
+               return &stop_sched_class;
+
+       return __setscheduler_class(p->policy, p->prio);
+}
+
 /*
  * 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
@@ -4241,8 +4249,7 @@ static void scx_disable_workfn(struct kthread_work *work)
        while ((p = scx_task_iter_next_locked(&sti))) {
                unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
                const struct sched_class *old_class = p->sched_class;
-               const struct sched_class *new_class =
-                       __setscheduler_class(p->policy, p->prio);
+               const struct sched_class *new_class = scx_setscheduler_class(p);
 
                update_rq_clock(task_rq(p));
 
@@ -5042,8 +5049,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
        while ((p = scx_task_iter_next_locked(&sti))) {
                unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
                const struct sched_class *old_class = p->sched_class;
-               const struct sched_class *new_class =
-                       __setscheduler_class(p->policy, p->prio);
+               const struct sched_class *new_class = scx_setscheduler_class(p);
 
                if (scx_get_task_state(p) != SCX_TASK_READY)
                        continue;