On 4/19/25 8:58 AM, Jordan Rife wrote:
static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter)
{
- while (iter->cur_sk < iter->end_sk)
- sock_put(iter->batch[iter->cur_sk++].sock);
+ union bpf_udp_iter_batch_item *item;
+ unsigned int cur_sk = iter->cur_sk;
+ __u64 cookie;
+
+ /* Remember the cookies of the sockets we haven't seen yet, so we can
+ * pick up where we left off next time around.
+ */
+ while (cur_sk < iter->end_sk) {
+ item = &iter->batch[cur_sk++];
+ cookie = __sock_gen_cookie(item->sock);
This can be called in the start/stop which is preemptible. I suspect this should
be sock_gen_cookie instead of __sock_gen_cookie. gen_cookie_next() is using
this_cpu_ptr.
+ sock_put(item->sock);
+ item->cookie = cookie;
+ }
}
