In the following loop:
while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) {
...
}
There is no external function call or any explict memory barrier
in the loop, the re-read of used->idx might be optimized and only
be retrieved once.
Use of voaltile normally should be prohibited, and access_once
is Linux kernel's style to handle this issue; Once we have that
macro in DPDK, we could change to that style.
virtio_recv_mergable_pkts might also have the same issue, so fix
it as well.
Fixes:
823ad647950a ("virtio: support multiple queues")
Fixes:
13ce5e7eb94f ("virtio: mergeable buffers")
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
virtqueue_notify(vq);
rte_rmb();
- while (vq->vq_used_cons_idx == vq->vq_ring.used->idx) {
+ while (VIRTQUEUE_NUSED(vq) == 0) {
rte_rmb();
usleep(100);
}
- while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) {
+ while (VIRTQUEUE_NUSED(vq)) {
uint32_t idx, desc_idx, used_idx;
struct vring_used_elem *uep;
struct vring_used {
uint16_t flags;
- uint16_t idx;
+ volatile uint16_t idx;
struct vring_used_elem ring[0];
};
if (unlikely(nb_pkts < RTE_VIRTIO_DESC_PER_LOOP))
return 0;
- nb_used = *(volatile uint16_t *)&vq->vq_ring.used->idx -
- vq->vq_used_cons_idx;
+ nb_used = VIRTQUEUE_NUSED(vq);
rte_compiler_barrier();