Memory barriers about buf_ring(9)

[rhenjau]

Hi, hackers
    I'm reading buf_ring(9) and have a question about the following
function. Is a memory barrier needed before br_cons_tail to prevent the
loading of br_ring[cons_head] load is reordered after br_cons_tail is set?
Producers may overwrite the area.

/*
 * single-consumer dequeue
 * use where dequeue is protected by a lock
 * e.g. a network driver's tx queue lock
 */
static __inline void *
buf_ring_dequeue_sc(struct buf_ring *br)
{
        uint32_t cons_head, cons_next;
#ifdef PREFETCH_DEFINED
        uint32_t cons_next_next;
#endif
        uint32_t prod_tail;
        void *buf;

        cons_head = br->br_cons_head;
        prod_tail = br->br_prod_tail;

        cons_next = (cons_head + 1) & br->br_cons_mask;
#ifdef PREFETCH_DEFINED
        cons_next_next = (cons_head + 2) & br->br_cons_mask;
#endif

        if (cons_head == prod_tail)
                return (NULL);

#ifdef PREFETCH_DEFINED
        if (cons_next != prod_tail) {
                prefetch(br->br_ring[cons_next]);
                if (cons_next_next != prod_tail)
                        prefetch(br->br_ring[cons_next_next]);
        }
#endif
        br->br_cons_head = cons_next;
        buf = br->br_ring[cons_head];

#ifdef DEBUG_BUFRING
        br->br_ring[cons_head] = NULL;
        if (!mtx_owned(br->br_lock))
                panic("lock not held on single consumer dequeue");
        if (br->br_cons_tail != cons_head)
                panic("inconsistent list cons_tail=%d cons_head=%d",
                    br->br_cons_tail, cons_head);
#endif
        ----------------------------------------------------- need memory
barrier?
        br->br_cons_tail = cons_next;
        return (buf);
}

-- 
-rhenjau