return (is_tx ^ (idx & 1)) == 0 && idx < nr_vring;
}
+static inline void
+do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+ struct batch_copy_elem *elem = vq->batch_copy_elems;
+ uint16_t count = vq->batch_copy_nb_elems;
+ int i;
+
+ for (i = 0; i < count; i++) {
+ rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
+ vhost_log_cache_write_iova(dev, vq, elem[i].log_addr,
+ elem[i].len);
+ PRINT_PACKET(dev, (uintptr_t)elem[i].dst, elem[i].len, 0);
+ }
+
+ vq->batch_copy_nb_elems = 0;
+}
+
+static inline void
+do_data_copy_dequeue(struct vhost_virtqueue *vq)
+{
+ struct batch_copy_elem *elem = vq->batch_copy_elems;
+ uint16_t count = vq->batch_copy_nb_elems;
+ int i;
+
+ for (i = 0; i < count; i++)
+ rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
+
+ vq->batch_copy_nb_elems = 0;
+}
+
static __rte_always_inline void
do_flush_shadow_used_ring_split(struct virtio_net *dev,
struct vhost_virtqueue *vq,
uint16_t i;
uint16_t flags;
+ if (vq->shadow_used_idx) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+
flags = PACKED_DESC_ENQUEUE_USED_FLAG(vq->used_wrap_counter);
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
vq_inc_last_used_packed(vq, count);
}
-static inline void
-do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
-{
- struct batch_copy_elem *elem = vq->batch_copy_elems;
- uint16_t count = vq->batch_copy_nb_elems;
- int i;
-
- for (i = 0; i < count; i++) {
- rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
- vhost_log_cache_write_iova(dev, vq, elem[i].log_addr,
- elem[i].len);
- PRINT_PACKET(dev, (uintptr_t)elem[i].dst, elem[i].len, 0);
- }
-
- vq->batch_copy_nb_elems = 0;
-}
-
-static inline void
-do_data_copy_dequeue(struct vhost_virtqueue *vq)
-{
- struct batch_copy_elem *elem = vq->batch_copy_elems;
- uint16_t count = vq->batch_copy_nb_elems;
- int i;
-
- for (i = 0; i < count; i++)
- rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
-
- vq->batch_copy_nb_elems = 0;
-}
-
static __rte_always_inline void
vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
}
}
-static __rte_always_inline void
-vhost_flush_dequeue_packed(struct virtio_net *dev,
- struct vhost_virtqueue *vq)
-{
- int shadow_count;
- if (!vq->shadow_used_idx)
- return;
-
- shadow_count = vq->last_used_idx - vq->shadow_last_used_idx;
- if (shadow_count <= 0)
- shadow_count += vq->size;
-
- if ((uint32_t)shadow_count >= (vq->size - MAX_PKT_BURST)) {
- do_data_copy_dequeue(vq);
- vhost_flush_dequeue_shadow_packed(dev, vq);
- vhost_vring_call_packed(dev, vq);
- }
-}
-
/* avoid write operation when necessary, to lessen cache issues */
#define ASSIGN_UNLESS_EQUAL(var, val) do { \
if ((var) != (val)) \
return pkt_idx;
}
-static __rte_always_inline bool
-next_desc_is_avail(const struct vhost_virtqueue *vq)
-{
- bool wrap_counter = vq->avail_wrap_counter;
- uint16_t next_used_idx = vq->last_used_idx + 1;
-
- if (next_used_idx >= vq->size) {
- next_used_idx -= vq->size;
- wrap_counter ^= 1;
- }
-
- return desc_is_avail(&vq->desc_packed[next_used_idx], wrap_counter);
-}
-
static __rte_noinline uint16_t
virtio_dev_tx_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
if (remained >= PACKED_BATCH_SIZE) {
if (!virtio_dev_tx_batch_packed(dev, vq, mbuf_pool,
&pkts[pkt_idx])) {
- vhost_flush_dequeue_packed(dev, vq);
pkt_idx += PACKED_BATCH_SIZE;
remained -= PACKED_BATCH_SIZE;
continue;
if (virtio_dev_tx_single_packed(dev, vq, mbuf_pool,
&pkts[pkt_idx]))
break;
- vhost_flush_dequeue_packed(dev, vq);
pkt_idx++;
remained--;
if (vq->shadow_used_idx) {
do_data_copy_dequeue(vq);
- if (remained && !next_desc_is_avail(vq)) {
- /*
- * The guest may be waiting to TX some buffers to
- * enqueue more to avoid bufferfloat, so we try to
- * reduce latency here.
- */
- vhost_flush_dequeue_shadow_packed(dev, vq);
- vhost_vring_call_packed(dev, vq);
- }
+ vhost_flush_dequeue_shadow_packed(dev, vq);
+ vhost_vring_call_packed(dev, vq);
}
return pkt_idx;
struct virtio_net *dev;
struct rte_mbuf *rarp_mbuf = NULL;
struct vhost_virtqueue *vq;
+ int16_t success = 1;
dev = get_device(vid);
if (!dev)
*
* broadcast_rarp shares a cacheline in the virtio_net structure
* with some fields that are accessed during enqueue and
- * rte_atomic16_cmpset() causes a write if using cmpxchg. This could
- * result in false sharing between enqueue and dequeue.
+ * __atomic_compare_exchange_n causes a write if performed compare
+ * and exchange. This could result in false sharing between enqueue
+ * and dequeue.
*
* Prevent unnecessary false sharing by reading broadcast_rarp first
- * and only performing cmpset if the read indicates it is likely to
- * be set.
+ * and only performing compare and exchange if the read indicates it
+ * is likely to be set.
*/
- if (unlikely(rte_atomic16_read(&dev->broadcast_rarp) &&
- rte_atomic16_cmpset((volatile uint16_t *)
- &dev->broadcast_rarp.cnt, 1, 0))) {
+ if (unlikely(__atomic_load_n(&dev->broadcast_rarp, __ATOMIC_ACQUIRE) &&
+ __atomic_compare_exchange_n(&dev->broadcast_rarp,
+ &success, 0, 0, __ATOMIC_RELEASE, __ATOMIC_RELAXED))) {
rarp_mbuf = rte_net_make_rarp_packet(mbuf_pool, &dev->mac);
if (rarp_mbuf == NULL) {