diff options
| author | Zqiang <qiang.zhang@linux.dev> | 2025-12-29 14:36:40 -0500 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-01-08 10:16:41 +0100 |
| commit | aeabe44c5019327f171973e357d634e42bf038cf (patch) | |
| tree | 3d48d2f2b603f6a0906fa2cfecbc463c9326b5c8 /kernel | |
| parent | b29d5e3a5625e1172518ae306ffd731a166e58c5 (diff) | |
| download | linux-aeabe44c5019327f171973e357d634e42bf038cf.tar.gz linux-aeabe44c5019327f171973e357d634e42bf038cf.tar.bz2 linux-aeabe44c5019327f171973e357d634e42bf038cf.zip | |
sched_ext: Fix incorrect sched_class settings for per-cpu migration tasks
[ Upstream commit 1dd6c84f1c544e552848a8968599220bd464e338 ]
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>
[ Adjust context ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/sched/ext.c | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 907eea83294c..6139263afd59 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -210,6 +210,14 @@ static struct scx_dispatch_q *find_user_dsq(struct scx_sched *sch, u64 dsq_id) return rhashtable_lookup_fast(&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 @@ -3994,8 +4002,7 @@ static void scx_disable_workfn(struct kthread_work *work) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { 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); struct sched_enq_and_set_ctx ctx; if (old_class != new_class && p->se.sched_delayed) @@ -4779,8 +4786,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { 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); struct sched_enq_and_set_ctx ctx; if (!tryget_task_struct(p)) |