used_idx -= vq->size;
}
- rte_smp_wmb();
-
for (i = 0; i < vq->shadow_used_idx; i++) {
uint16_t flags;
}
}
- vq->desc_packed[head_idx].flags = head_flags;
+ __atomic_store_n(&vq->desc_packed[head_idx].flags, head_flags,
+ __ATOMIC_RELEASE);
vhost_log_cache_used_vring(dev, vq,
head_idx *
if (unlikely(!desc_addr))
return -1;
+ rte_prefetch0((void *)(uintptr_t)desc_addr);
+
buf_vec[vec_id].buf_iova = desc_iova;
buf_vec[vec_id].buf_addr = desc_addr;
buf_vec[vec_id].buf_len = desc_chunck_len;
* The indirect desc table is not contiguous
* in process VA space, we have to copy it.
*/
- idesc = alloc_copy_ind_table(dev, vq,
+ idesc = vhost_alloc_copy_ind_table(dev, vq,
vq->desc[idx].addr, vq->desc[idx].len);
if (unlikely(!idesc))
return -1;
* The indirect desc table is not contiguous
* in process VA space, we have to copy it.
*/
- idescs = alloc_copy_ind_table(dev, vq, desc->addr, desc->len);
+ idescs = vhost_alloc_copy_ind_table(dev,
+ vq, desc->addr, desc->len);
if (unlikely(!idescs))
return -1;
if (avail_idx < vq->last_avail_idx)
wrap_counter ^= 1;
- if (unlikely(!desc_is_avail(&descs[avail_idx], wrap_counter)))
- return -1;
-
/*
- * The ordering between desc flags and desc
- * content reads need to be enforced.
+ * Perform a load-acquire barrier in desc_is_avail to
+ * enforce the ordering between desc flags and desc
+ * content.
*/
- rte_smp_rmb();
+ if (unlikely(!desc_is_avail(&descs[avail_idx], wrap_counter)))
+ return -1;
*desc_count = 0;
*len = 0;
return 0;
}
+static __rte_noinline void
+copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct buf_vector *buf_vec,
+ struct virtio_net_hdr_mrg_rxbuf *hdr)
+{
+ uint64_t len;
+ uint64_t remain = dev->vhost_hlen;
+ uint64_t src = (uint64_t)(uintptr_t)hdr, dst;
+ uint64_t iova = buf_vec->buf_iova;
+
+ while (remain) {
+ len = RTE_MIN(remain,
+ buf_vec->buf_len);
+ dst = buf_vec->buf_addr;
+ rte_memcpy((void *)(uintptr_t)dst,
+ (void *)(uintptr_t)src,
+ len);
+
+ PRINT_PACKET(dev, (uintptr_t)dst,
+ (uint32_t)len, 0);
+ vhost_log_cache_write(dev, vq,
+ iova, len);
+
+ remain -= len;
+ iova += len;
+ src += len;
+ buf_vec++;
+ }
+}
+
static __rte_always_inline int
copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf *m, struct buf_vector *buf_vec,
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- if (nr_vec > 1)
- rte_prefetch0((void *)(uintptr_t)buf_vec[1].buf_addr);
-
if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
error = -1;
goto out;
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- /* Prefetch next buffer address. */
- if (vec_idx + 1 < nr_vec)
- rte_prefetch0((void *)(uintptr_t)
- buf_vec[vec_idx + 1].buf_addr);
buf_offset = 0;
buf_avail = buf_len;
}
num_buffers);
if (unlikely(hdr == &tmp_hdr)) {
- uint64_t len;
- uint64_t remain = dev->vhost_hlen;
- uint64_t src = (uint64_t)(uintptr_t)hdr, dst;
- uint64_t iova = buf_vec[0].buf_iova;
- uint16_t hdr_vec_idx = 0;
-
- while (remain) {
- len = RTE_MIN(remain,
- buf_vec[hdr_vec_idx].buf_len);
- dst = buf_vec[hdr_vec_idx].buf_addr;
- rte_memcpy((void *)(uintptr_t)dst,
- (void *)(uintptr_t)src,
- len);
-
- PRINT_PACKET(dev, (uintptr_t)dst,
- (uint32_t)len, 0);
- vhost_log_cache_write(dev, vq,
- iova, len);
-
- remain -= len;
- iova += len;
- src += len;
- hdr_vec_idx++;
- }
+ copy_vnet_hdr_to_desc(dev, vq, buf_vec, hdr);
} else {
PRINT_PACKET(dev, (uintptr_t)hdr_addr,
dev->vhost_hlen, 0);
return error;
}
-static __rte_always_inline uint32_t
+static __rte_noinline uint32_t
virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf **pkts, uint32_t count)
{
break;
}
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
VHOST_LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
return pkt_idx;
}
-static __rte_always_inline uint32_t
+static __rte_noinline uint32_t
virtio_dev_rx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf **pkts, uint32_t count)
{
break;
}
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
VHOST_LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
}
}
+static __rte_noinline void
+copy_vnet_hdr_from_desc(struct virtio_net_hdr *hdr,
+ struct buf_vector *buf_vec)
+{
+ uint64_t len;
+ uint64_t remain = sizeof(struct virtio_net_hdr);
+ uint64_t src;
+ uint64_t dst = (uint64_t)(uintptr_t)hdr;
+
+ while (remain) {
+ len = RTE_MIN(remain, buf_vec->buf_len);
+ src = buf_vec->buf_addr;
+ rte_memcpy((void *)(uintptr_t)dst,
+ (void *)(uintptr_t)src, len);
+
+ remain -= len;
+ dst += len;
+ buf_vec++;
+ }
+}
+
static __rte_always_inline int
copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct buf_vector *buf_vec, uint16_t nr_vec,
goto out;
}
- if (likely(nr_vec > 1))
- rte_prefetch0((void *)(uintptr_t)buf_vec[1].buf_addr);
-
if (virtio_net_with_host_offload(dev)) {
if (unlikely(buf_len < sizeof(struct virtio_net_hdr))) {
- uint64_t len;
- uint64_t remain = sizeof(struct virtio_net_hdr);
- uint64_t src;
- uint64_t dst = (uint64_t)(uintptr_t)&tmp_hdr;
- uint16_t hdr_vec_idx = 0;
-
/*
* No luck, the virtio-net header doesn't fit
* in a contiguous virtual area.
*/
- while (remain) {
- len = RTE_MIN(remain,
- buf_vec[hdr_vec_idx].buf_len);
- src = buf_vec[hdr_vec_idx].buf_addr;
- rte_memcpy((void *)(uintptr_t)dst,
- (void *)(uintptr_t)src, len);
-
- remain -= len;
- dst += len;
- hdr_vec_idx++;
- }
-
+ copy_vnet_hdr_from_desc(&tmp_hdr, buf_vec);
hdr = &tmp_hdr;
} else {
hdr = (struct virtio_net_hdr *)((uintptr_t)buf_addr);
- rte_prefetch0(hdr);
}
}
buf_avail = buf_vec[vec_idx].buf_len - dev->vhost_hlen;
}
- rte_prefetch0((void *)(uintptr_t)
- (buf_addr + buf_offset));
-
PRINT_PACKET(dev,
(uintptr_t)(buf_addr + buf_offset),
(uint32_t)buf_avail, 0);
buf_iova = buf_vec[vec_idx].buf_iova;
buf_len = buf_vec[vec_idx].buf_len;
- /*
- * Prefecth desc n + 1 buffer while
- * desc n buffer is processed.
- */
- if (vec_idx + 1 < nr_vec)
- rte_prefetch0((void *)(uintptr_t)
- buf_vec[vec_idx + 1].buf_addr);
-
buf_offset = 0;
buf_avail = buf_len;
return NULL;
}
-static __rte_always_inline uint16_t
+static __rte_noinline uint16_t
virtio_dev_tx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
{
if (likely(dev->dequeue_zero_copy == 0))
update_shadow_used_ring_split(vq, head_idx, 0);
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(pkts[i] == NULL)) {
RTE_LOG(ERR, VHOST_DATA,
return i;
}
-static __rte_always_inline uint16_t
+static __rte_noinline uint16_t
virtio_dev_tx_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
{
update_shadow_used_ring_packed(vq, buf_id, 0,
desc_count);
- rte_prefetch0((void *)(uintptr_t)buf_vec[0].buf_addr);
-
pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(pkts[i] == NULL)) {
RTE_LOG(ERR, VHOST_DATA,