sched_ext: Enforce scheduler ownership when updating slice and dsq_vtime

scx_bpf_task_set_slice() and scx_bpf_task_set_dsq_vtime() now verify that
the calling scheduler has authority over the task before allowing updates.
This prevents schedulers from modifying tasks that don't belong to them in
hierarchical scheduling configurations.

Direct writes to p->scx.slice and p->scx.dsq_vtime are deprecated and now
trigger warnings. They will be disallowed in a future release.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index bfe0f0c38ef78123a7952b98f51ffaca83917506..beb0e3443209758012793857cdf35d899ff2dc8c 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5945,12 +5945,17 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
 
        t = btf_type_by_id(reg->btf, reg->btf_id);
        if (t == task_struct_type) {
-               if (off >= offsetof(struct task_struct, scx.slice) &&
-                   off + size <= offsetofend(struct task_struct, scx.slice))
-                       return SCALAR_VALUE;
-               if (off >= offsetof(struct task_struct, scx.dsq_vtime) &&
-                   off + size <= offsetofend(struct task_struct, scx.dsq_vtime))
+               /*
+                * COMPAT: Will be removed in v6.23.
+                */
+               if ((off >= offsetof(struct task_struct, scx.slice) &&
+                    off + size <= offsetofend(struct task_struct, scx.slice)) ||
+                   (off >= offsetof(struct task_struct, scx.dsq_vtime) &&
+                    off + size <= offsetofend(struct task_struct, scx.dsq_vtime))) {
+                       pr_warn("sched_ext: Writing directly to p->scx.slice/dsq_vtime is deprecated, use scx_bpf_task_set_slice/dsq_vtime()");
                        return SCALAR_VALUE;
+               }
+
                if (off >= offsetof(struct task_struct, scx.disallow) &&
                    off + size <= offsetofend(struct task_struct, scx.disallow))
                        return SCALAR_VALUE;
@@ -7163,12 +7168,21 @@ __bpf_kfunc_start_defs();
  * scx_bpf_task_set_slice - Set task's time slice
  * @p: task of interest
  * @slice: time slice to set in nsecs
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
  *
  * Set @p's time slice to @slice. Returns %true on success, %false if the
  * calling scheduler doesn't have authority over @p.
  */
-__bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice)
+__bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice,
+                                       const struct bpf_prog_aux *aux)
 {
+       struct scx_sched *sch;
+
+       guard(rcu)();
+       sch = scx_prog_sched(aux);
+       if (unlikely(!scx_task_on_sched(sch, p)))
+               return false;
+
        p->scx.slice = slice;
        return true;
 }
@@ -7177,12 +7191,21 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice)
  * scx_bpf_task_set_dsq_vtime - Set task's virtual time for DSQ ordering
  * @p: task of interest
  * @vtime: virtual time to set
+ * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
  *
  * Set @p's virtual time to @vtime. Returns %true on success, %false if the
  * calling scheduler doesn't have authority over @p.
  */
-__bpf_kfunc bool scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime)
+__bpf_kfunc bool scx_bpf_task_set_dsq_vtime(struct task_struct *p, u64 vtime,
+                                           const struct bpf_prog_aux *aux)
 {
+       struct scx_sched *sch;
+
+       guard(rcu)();
+       sch = scx_prog_sched(aux);
+       if (unlikely(!scx_task_on_sched(sch, p)))
+               return false;
+
        p->scx.dsq_vtime = vtime;
        return true;
 }
@@ -8062,8 +8085,8 @@ __bpf_kfunc void scx_bpf_events(struct scx_event_stats *events,
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(scx_kfunc_ids_any)
-BTF_ID_FLAGS(func, scx_bpf_task_set_slice, KF_RCU);
-BTF_ID_FLAGS(func, scx_bpf_task_set_dsq_vtime, KF_RCU);
+BTF_ID_FLAGS(func, scx_bpf_task_set_slice, KF_IMPLICIT_ARGS | KF_RCU);
+BTF_ID_FLAGS(func, scx_bpf_task_set_dsq_vtime, KF_IMPLICIT_ARGS | KF_RCU);
 BTF_ID_FLAGS(func, scx_bpf_kick_cpu, KF_IMPLICIT_ARGS)
 BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued)
 BTF_ID_FLAGS(func, scx_bpf_destroy_dsq)