C++ eBPF： 在将栈变量存储到映射中时超出BPF堆栈限制

我有以下eBPF计划:

#include <stdio.h>
#include <string.h>

#include <linux/bpf.h>
#include <sys/socket.h>

#include <bpf/bpf_helpers.h>

char LICENSE[] SEC("license") = "GPL";

// msg_data_map carries a key-value pair of (msg_id, msg_length), and can record
// upto 65535 messages at once.
#define MAX_MSG_LEN 128
struct {
  __uint(type, BPF_MAP_TYPE_HASH);
  __uint(max_entries, 65535);
  __type(key, int);
  __type(value, char[MAX_MSG_LEN]);
} msg_data_map SEC(".maps");

SEC("sk_msg")
int msg_prog(struct sk_msg_md *msg) {
  long len = (long)msg->data_end - (long)msg->data;

  void *data_end = (void *)(long) msg->data_end;
  void *data = (void *)(long) msg->data;

  // Bounds check to make verifier happy
  if (data + MAX_MSG_LEN > data_end) {
    return SK_PASS;
  }

  char buf[MAX_MSG_LEN] = {0};
  if (len > MAX_MSG_LEN) {
    __builtin_memcpy(buf, data, MAX_MSG_LEN);
  } else {
    __builtin_memcpy(buf, data, len);
  }

  // Update in map
  int index = 0;
  bpf_map_update_elem(&msg_data_map, &index, &buf, BPF_ANY);
 
  return SK_PASS;
}

编译上述程序会出现以下错误:

Looks like the BPF stack limit of 512 bytes is exceeded. Please move large on stack variables into BPF per-cpu array map.

1. 因为buf数组只有128个字节，所以它不应该超过堆栈限制.
2. 如果我注释 map 更新行，程序编译得很好.为何会是这样呢？