What were you trying to do that didn't work?

```
bpf-runqlen 1 1
```

What is the impact of this issue to you?

Unable to do fine-grain troubleshooting of cpu scheduler queue len

Please provide the package NVR for which the bug is seen:

libbpf-tools-0.32.0-1.el10.x86_64

How reproducible is this bug?:

Always

Steps to reproduce

1. bpf-runqlen 1 1

Expected results

Queue length distribution

Actual results

```
libbpf: prog 'do_sample': BPF program load failed: Invalid argument
libbpf: prog 'do_sample': – BEGIN PROG LOAD LOG –
0: R1=ctx() R10=fp0
; task = (void*)bpf_get_current_task(); @ runqlen.bpf.c:21
0: (85) call bpf_get_current_task#35 ; R0_w=scalar()
; if (targ_host) @ runqlen.bpf.c:22
1: (18) r1 = 0xffffa01ac0c0c001 ; R1_w=map_value(map=runqlen_.rodata,ks=4,vs=2,off=1)
3: (71) r1 = *(u8 *)(r1 +0) ; R1_w=0
4: (55) if r1 != 0x1 goto pc+16 ; R1_w=0
; slot = BPF_CORE_READ(task, se.cfs_rq, rq, nr_running); @ runqlen.bpf.c:23
21: (b7) r1 = 288 ; R1_w=288
22: (0f) r0 += r1 ; R0_w=scalar() R1_w=288
23: (bf) r1 = r10 ; R1_w=fp0 R10=fp0
24: (07) r1 += -16 ; R1_w=fp-16
; slot = BPF_CORE_READ(task, se.cfs_rq, nr_running); @ runqlen.bpf.c:25
25: (b7) r2 = 8 ; R2_w=8
26: (bf) r3 = r0 ; R0_w=scalar(id=1) R3_w=scalar(id=1)
27: (85) call bpf_probe_read_kernel#113 ; R0=scalar() fp-16=mmmmmmmm
28: <invalid CO-RE relocation>
failed to resolve CO-RE relocation <byte_off> [349] struct cfs_rq.nr_running (0:1 @ offset 16)
processed 12 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 0
– END PROG LOAD LOG –
libbpf: prog 'do_sample': failed to load: -22
libbpf: failed to load object 'runqlen_bpf'
libbpf: failed to load BPF skeleton 'runqlen_bpf': -22
failed to load BPF object: -22
```

See here: https://testing.stream.centos.org/job/CentOS_10-stream_x86_64_kvm//HTML_20Test_20Results/