why does `synchronize_rcu()` not deadlock when beening called inside a read lock block?

synchronize_rcu() is used to waits only for ongoing RCU read-side critical sections to complete. If so, it should been blocked forever when beening called inside a read block. However, the following code works well on my linux kernel, why?

void port_range_clean( void ) 
{
    struct port_range *p;

redo:
    rcu_read_lock();
    list_for_each_entry_rcu(p, &port_rt->ports, list) {
        list_del_rcu(&p->list);
        synchronize_rcu();
         rcu_read_unlock();           
        kfree(p);
        goto redo;
    }
}

I do not really understand what do you wrote, but you have a lock call outside of the redo loop and an unlock inside the loop.
Also your code is incomplete.

void list_clean( void ) 
{
    struct port_range *p;
    list_for_each_entry_rcu(p, &port_rt->ports, list) {
        list_del_rcu(&p->list);    
        kfree(p);
        goto redo;
    }
}

The original code is to clean a list, delete from first to the last.

rcu_read_lock();
synchronize_rcu();  // deadlock?
rcu_read_unlock();

What I really care is why synchronize_rcu() not cause dead lock?