sched_ext: Guard scx_dsq_move() against NULL kit->dsq after failed iter_new

bpf_iter_scx_dsq_new() clears kit->dsq on failure and
bpf_iter_scx_dsq_{next,destroy}() guard against that. scx_dsq_move() doesn't -
it dereferences kit->dsq immediately, so a BPF program that calls
scx_bpf_dsq_move[_vtime]() after a failed iter_new oopses the kernel.

Return false if kit->dsq is NULL.

Fixes: 4c30f5ce4f7a ("sched_ext: Implement scx_bpf_dispatch[_vtime]_from_dsq()")
Cc: stable@vger.kernel.org # v6.12+
Reported-by: Chris Mason <clm@meta.com>
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 7f991ecb1398756b34a6a9c1393f7ecf2c2465dd..68c67113204fa8c95242b5ba19ac20ade6a72c6a 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -8076,12 +8076,22 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
                         struct task_struct *p, u64 dsq_id, u64 enq_flags)
 {
        struct scx_dispatch_q *src_dsq = kit->dsq, *dst_dsq;
-       struct scx_sched *sch = src_dsq->sched;
+       struct scx_sched *sch;
        struct rq *this_rq, *src_rq, *locked_rq;
        bool dispatched = false;
        bool in_balance;
        unsigned long flags;
 
+       /*
+        * The verifier considers an iterator slot initialized on any
+        * KF_ITER_NEW return, so a BPF program may legally reach here after
+        * bpf_iter_scx_dsq_new() failed and left @kit->dsq NULL.
+        */
+       if (unlikely(!src_dsq))
+               return false;
+
+       sch = src_dsq->sched;
+
        if (!scx_vet_enq_flags(sch, dsq_id, &enq_flags))
                return false;