#include <rte_mbuf.h>
#include <rte_memcpy.h>
+#include <rte_net.h>
#include <rte_ether.h>
#include <rte_ip.h>
#include <rte_vhost.h>
{
uint16_t i;
uint16_t flags;
+ uint16_t last_used_idx;
+ struct vring_packed_desc *desc_base;
- if (vq->shadow_used_idx) {
- do_data_copy_enqueue(dev, vq);
- vhost_flush_enqueue_shadow_packed(dev, vq);
- }
+ last_used_idx = vq->last_used_idx;
+ desc_base = &vq->desc_packed[last_used_idx];
flags = PACKED_DESC_ENQUEUE_USED_FLAG(vq->used_wrap_counter);
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
- vq->desc_packed[vq->last_used_idx + i].id = ids[i];
- vq->desc_packed[vq->last_used_idx + i].len = lens[i];
+ desc_base[i].id = ids[i];
+ desc_base[i].len = lens[i];
}
rte_atomic_thread_fence(__ATOMIC_RELEASE);
- vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
- vq->desc_packed[vq->last_used_idx + i].flags = flags;
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ desc_base[i].flags = flags;
+ }
- vhost_log_cache_used_vring(dev, vq, vq->last_used_idx *
+ vhost_log_cache_used_vring(dev, vq, last_used_idx *
sizeof(struct vring_packed_desc),
sizeof(struct vring_packed_desc) *
PACKED_BATCH_SIZE);
}
static __rte_always_inline void
-vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
- struct vhost_virtqueue *vq,
- uint32_t len[],
- uint16_t id[],
- uint16_t count[],
+vhost_shadow_enqueue_packed(struct vhost_virtqueue *vq,
+ uint32_t *len,
+ uint16_t *id,
+ uint16_t *count,
uint16_t num_buffers)
{
uint16_t i;
+
for (i = 0; i < num_buffers; i++) {
/* enqueue shadow flush action aligned with batch num */
if (!vq->shadow_used_idx)
vq->shadow_aligned_idx += count[i];
vq->shadow_used_idx++;
}
+}
+
+static __rte_always_inline void
+vhost_shadow_enqueue_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint32_t *len,
+ uint16_t *id,
+ uint16_t *count,
+ uint16_t num_buffers)
+{
+ vhost_shadow_enqueue_packed(vq, len, id, count, num_buffers);
if (vq->shadow_aligned_idx >= PACKED_BATCH_SIZE) {
do_data_copy_enqueue(dev, vq);
}
static __rte_always_inline int
-virtio_dev_rx_batch_packed(struct virtio_net *dev,
+virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
struct vhost_virtqueue *vq,
- struct rte_mbuf **pkts)
+ struct rte_mbuf **pkts,
+ uint64_t *desc_addrs,
+ uint64_t *lens)
{
bool wrap_counter = vq->avail_wrap_counter;
struct vring_packed_desc *descs = vq->desc_packed;
uint16_t avail_idx = vq->last_avail_idx;
- uint64_t desc_addrs[PACKED_BATCH_SIZE];
- struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_BATCH_SIZE];
uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
- uint64_t lens[PACKED_BATCH_SIZE];
- uint16_t ids[PACKED_BATCH_SIZE];
uint16_t i;
if (unlikely(avail_idx & PACKED_BATCH_MASK))
return -1;
}
+ return 0;
+}
+
+static __rte_always_inline int
+virtio_dev_rx_async_batch_check(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts,
+ uint64_t *desc_addrs,
+ uint64_t *lens)
+{
+ bool wrap_counter = vq->avail_wrap_counter;
+ struct vring_packed_desc *descs = vq->desc_packed;
+ uint16_t avail_idx = vq->last_avail_idx;
+ uint16_t used_idx = vq->last_used_idx;
+ uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ uint32_t cpy_threshold = vq->async_threshold;
+ uint16_t i;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(pkts[i]->data_len >= cpy_threshold))
+ return -1;
+ }
+
+ if (unlikely(avail_idx & PACKED_BATCH_MASK))
+ return -1;
+
+ if (unlikely((avail_idx + PACKED_BATCH_SIZE) > vq->size))
+ return -1;
+
+ if (unlikely((used_idx + PACKED_BATCH_SIZE) > vq->size))
+ return -1;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(pkts[i]->next != NULL))
+ return -1;
+ if (unlikely(!desc_is_avail(&descs[avail_idx + i],
+ wrap_counter)))
+ return -1;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ lens[i] = descs[avail_idx + i].len;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(pkts[i]->pkt_len > (lens[i] - buf_offset)))
+ return -1;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ desc_addrs[i] = vhost_iova_to_vva(dev, vq,
+ descs[avail_idx + i].addr,
+ &lens[i],
+ VHOST_ACCESS_RW);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(!desc_addrs[i]))
+ return -1;
+ if (unlikely(lens[i] != descs[avail_idx + i].len))
+ return -1;
+ }
+
+ return 0;
+}
+
+static __rte_always_inline void
+virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts,
+ uint64_t *desc_addrs,
+ uint64_t *lens)
+{
+ uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ struct virtio_net_hdr_mrg_rxbuf *hdrs[PACKED_BATCH_SIZE];
+ struct vring_packed_desc *descs = vq->desc_packed;
+ uint16_t avail_idx = vq->last_avail_idx;
+ uint16_t ids[PACKED_BATCH_SIZE];
+ uint16_t i;
+
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
rte_prefetch0((void *)(uintptr_t)desc_addrs[i]);
hdrs[i] = (struct virtio_net_hdr_mrg_rxbuf *)
ids[i] = descs[avail_idx + i].id;
vhost_flush_enqueue_batch_packed(dev, vq, lens, ids);
+}
+
+static __rte_always_inline int
+virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts)
+{
+ uint64_t desc_addrs[PACKED_BATCH_SIZE];
+ uint64_t lens[PACKED_BATCH_SIZE];
+
+ if (virtio_dev_rx_sync_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+ return -1;
+
+ if (vq->shadow_used_idx) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+
+ virtio_dev_rx_batch_packed_copy(dev, vq, pkts, desc_addrs, lens);
+
+ return 0;
+}
+
+static __rte_always_inline int
+virtio_dev_rx_async_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts,
+ struct rte_mbuf **comp_pkts, uint32_t *pkt_done)
+{
+ uint16_t i;
+ uint64_t desc_addrs[PACKED_BATCH_SIZE];
+ uint64_t lens[PACKED_BATCH_SIZE];
+
+ if (virtio_dev_rx_async_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+ return -1;
+
+ virtio_dev_rx_batch_packed_copy(dev, vq, pkts, desc_addrs, lens);
+
+ if (vq->shadow_used_idx) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ comp_pkts[(*pkt_done)++] = pkts[i];
return 0;
}
uint32_t count)
{
uint32_t pkt_idx = 0;
- uint32_t remained = count;
do {
rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
- if (remained >= PACKED_BATCH_SIZE) {
- if (!virtio_dev_rx_batch_packed(dev, vq,
+ if (count - pkt_idx >= PACKED_BATCH_SIZE) {
+ if (!virtio_dev_rx_sync_batch_packed(dev, vq,
&pkts[pkt_idx])) {
pkt_idx += PACKED_BATCH_SIZE;
- remained -= PACKED_BATCH_SIZE;
continue;
}
}
if (virtio_dev_rx_single_packed(dev, vq, pkts[pkt_idx]))
break;
pkt_idx++;
- remained--;
} while (pkt_idx < count);
uint16_t vq_size, uint16_t n_inflight)
{
return pkts_idx > n_inflight ? (pkts_idx - n_inflight) :
- (vq_size - n_inflight + pkts_idx) & (vq_size - 1);
+ (vq_size - n_inflight + pkts_idx) % vq_size;
+}
+
+static __rte_always_inline void
+store_dma_desc_info_split(struct vring_used_elem *s_ring, struct vring_used_elem *d_ring,
+ uint16_t ring_size, uint16_t s_idx, uint16_t d_idx, uint16_t count)
+{
+ size_t elem_size = sizeof(struct vring_used_elem);
+
+ if (d_idx + count <= ring_size) {
+ rte_memcpy(d_ring + d_idx, s_ring + s_idx, count * elem_size);
+ } else {
+ uint16_t size = ring_size - d_idx;
+
+ rte_memcpy(d_ring + d_idx, s_ring + s_idx, size * elem_size);
+ rte_memcpy(d_ring, s_ring + s_idx + size, (count - size) * elem_size);
+ }
+}
+
+static __rte_always_inline void
+store_dma_desc_info_packed(struct vring_used_elem_packed *s_ring,
+ struct vring_used_elem_packed *d_ring,
+ uint16_t ring_size, uint16_t s_idx, uint16_t d_idx, uint16_t count)
+{
+ size_t elem_size = sizeof(struct vring_used_elem_packed);
+
+ if (d_idx + count <= ring_size) {
+ rte_memcpy(d_ring + d_idx, s_ring + s_idx, count * elem_size);
+ } else {
+ uint16_t size = ring_size - d_idx;
+
+ rte_memcpy(d_ring + d_idx, s_ring + s_idx, size * elem_size);
+ rte_memcpy(d_ring, s_ring + s_idx + size, (count - size) * elem_size);
+ }
}
static __rte_noinline uint32_t
struct rte_vhost_async_desc tdes[MAX_PKT_BURST];
struct iovec *src_iovec = vec_pool;
struct iovec *dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
- struct rte_vhost_iov_iter *src_it = it_pool;
- struct rte_vhost_iov_iter *dst_it = it_pool + 1;
uint16_t slot_idx = 0;
uint16_t segs_await = 0;
+ uint16_t iovec_idx = 0, it_idx = 0;
struct async_inflight_info *pkts_info = vq->async_pkts_info;
uint32_t n_pkts = 0, pkt_err = 0;
uint32_t num_async_pkts = 0, num_done_pkts = 0;
+ int32_t n_xfer;
struct {
uint16_t pkt_idx;
uint16_t last_avail_idx;
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
- if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx],
- buf_vec, nr_vec, num_buffers,
- src_iovec, dst_iovec, src_it, dst_it) < 0) {
+ if (async_mbuf_to_desc(dev, vq, pkts[pkt_idx], buf_vec, nr_vec, num_buffers,
+ &src_iovec[iovec_idx], &dst_iovec[iovec_idx],
+ &it_pool[it_idx], &it_pool[it_idx + 1]) < 0) {
vq->shadow_used_idx -= num_buffers;
break;
}
slot_idx = (vq->async_pkts_idx + num_async_pkts) &
(vq->size - 1);
- if (src_it->count) {
+ if (it_pool[it_idx].count) {
uint16_t from, to;
- async_fill_desc(&tdes[pkt_burst_idx++], src_it, dst_it);
+ async_fill_desc(&tdes[pkt_burst_idx++],
+ &it_pool[it_idx], &it_pool[it_idx + 1]);
pkts_info[slot_idx].descs = num_buffers;
pkts_info[slot_idx].mbuf = pkts[pkt_idx];
async_pkts_log[num_async_pkts].pkt_idx = pkt_idx;
async_pkts_log[num_async_pkts++].last_avail_idx =
vq->last_avail_idx;
- src_iovec += src_it->nr_segs;
- dst_iovec += dst_it->nr_segs;
- src_it += 2;
- dst_it += 2;
- segs_await += src_it->nr_segs;
+
+ iovec_idx += it_pool[it_idx].nr_segs;
+ it_idx += 2;
+
+ segs_await += it_pool[it_idx].nr_segs;
/**
* recover shadow used ring and keep DMA-occupied
* descriptors.
*/
from = vq->shadow_used_idx - num_buffers;
- to = vq->async_desc_idx & (vq->size - 1);
- if (num_buffers + to <= vq->size) {
- rte_memcpy(&vq->async_descs_split[to],
- &vq->shadow_used_split[from],
- num_buffers *
- sizeof(struct vring_used_elem));
- } else {
- int size = vq->size - to;
-
- rte_memcpy(&vq->async_descs_split[to],
- &vq->shadow_used_split[from],
- size *
- sizeof(struct vring_used_elem));
- rte_memcpy(vq->async_descs_split,
- &vq->shadow_used_split[from +
- size], (num_buffers - size) *
- sizeof(struct vring_used_elem));
- }
- vq->async_desc_idx += num_buffers;
+ to = vq->async_desc_idx_split & (vq->size - 1);
+
+ store_dma_desc_info_split(vq->shadow_used_split,
+ vq->async_descs_split, vq->size, from, to, num_buffers);
+
+ vq->async_desc_idx_split += num_buffers;
vq->shadow_used_idx -= num_buffers;
} else
comp_pkts[num_done_pkts++] = pkts[pkt_idx];
if (unlikely(pkt_burst_idx >= VHOST_ASYNC_BATCH_THRESHOLD ||
((VHOST_MAX_ASYNC_VEC >> 1) - segs_await <
BUF_VECTOR_MAX))) {
- n_pkts = vq->async_ops.transfer_data(dev->vid,
+ n_xfer = vq->async_ops.transfer_data(dev->vid,
queue_id, tdes, 0, pkt_burst_idx);
- src_iovec = vec_pool;
- dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
- src_it = it_pool;
- dst_it = it_pool + 1;
+ if (n_xfer >= 0) {
+ n_pkts = n_xfer;
+ } else {
+ VHOST_LOG_DATA(ERR,
+ "(%d) %s: failed to transfer data for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ n_pkts = 0;
+ }
+
+ iovec_idx = 0;
+ it_idx = 0;
+
segs_await = 0;
vq->async_pkts_inflight_n += n_pkts;
}
if (pkt_burst_idx) {
- n_pkts = vq->async_ops.transfer_data(dev->vid,
- queue_id, tdes, 0, pkt_burst_idx);
+ n_xfer = vq->async_ops.transfer_data(dev->vid, queue_id, tdes, 0, pkt_burst_idx);
+ if (n_xfer >= 0) {
+ n_pkts = n_xfer;
+ } else {
+ VHOST_LOG_DATA(ERR, "(%d) %s: failed to transfer data for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ n_pkts = 0;
+ }
+
vq->async_pkts_inflight_n += n_pkts;
if (unlikely(n_pkts < pkt_burst_idx))
num_descs += pkts_info[slot_idx & (vq->size - 1)].descs;
slot_idx--;
}
- vq->async_desc_idx -= num_descs;
+ vq->async_desc_idx_split -= num_descs;
/* recover shadow used ring and available ring */
vq->shadow_used_idx -= (vq->last_avail_idx -
async_pkts_log[num_async_pkts].last_avail_idx -
return pkt_idx;
}
-uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+static __rte_always_inline void
+vhost_update_used_packed(struct vhost_virtqueue *vq,
+ struct vring_used_elem_packed *shadow_ring,
+ uint16_t count)
{
- struct virtio_net *dev = get_device(vid);
- struct vhost_virtqueue *vq;
- uint16_t n_pkts_cpl = 0, n_pkts_put = 0, n_descs = 0;
- uint16_t start_idx, pkts_idx, vq_size;
- struct async_inflight_info *pkts_info;
- uint16_t from, i;
-
- if (!dev)
- return 0;
+ int i;
+ uint16_t used_idx = vq->last_used_idx;
+ uint16_t head_idx = vq->last_used_idx;
+ uint16_t head_flags = 0;
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
- }
+ if (count == 0)
+ return;
- vq = dev->virtqueue[queue_id];
+ /* Split loop in two to save memory barriers */
+ for (i = 0; i < count; i++) {
+ vq->desc_packed[used_idx].id = shadow_ring[i].id;
+ vq->desc_packed[used_idx].len = shadow_ring[i].len;
- if (unlikely(!vq->async_registered)) {
- VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
+ used_idx += shadow_ring[i].count;
+ if (used_idx >= vq->size)
+ used_idx -= vq->size;
}
- rte_spinlock_lock(&vq->access_lock);
-
- pkts_idx = vq->async_pkts_idx & (vq->size - 1);
- pkts_info = vq->async_pkts_info;
- vq_size = vq->size;
- start_idx = virtio_dev_rx_async_get_info_idx(pkts_idx,
- vq_size, vq->async_pkts_inflight_n);
-
- if (count > vq->async_last_pkts_n)
- n_pkts_cpl = vq->async_ops.check_completed_copies(vid,
- queue_id, 0, count - vq->async_last_pkts_n);
- n_pkts_cpl += vq->async_last_pkts_n;
-
- n_pkts_put = RTE_MIN(count, n_pkts_cpl);
- if (unlikely(n_pkts_put == 0)) {
- vq->async_last_pkts_n = n_pkts_cpl;
- goto done;
- }
+ /* The ordering for storing desc flags needs to be enforced. */
+ rte_atomic_thread_fence(__ATOMIC_RELEASE);
- for (i = 0; i < n_pkts_put; i++) {
- from = (start_idx + i) & (vq_size - 1);
- n_descs += pkts_info[from].descs;
- pkts[i] = pkts_info[from].mbuf;
- }
- vq->async_last_pkts_n = n_pkts_cpl - n_pkts_put;
- vq->async_pkts_inflight_n -= n_pkts_put;
+ for (i = 0; i < count; i++) {
+ uint16_t flags;
- if (likely(vq->enabled && vq->access_ok)) {
- uint16_t nr_left = n_descs;
- uint16_t nr_copy;
- uint16_t to;
-
- /* write back completed descriptors to used ring */
- do {
- from = vq->last_async_desc_idx & (vq->size - 1);
- nr_copy = nr_left + from <= vq->size ? nr_left :
- vq->size - from;
- to = vq->last_used_idx & (vq->size - 1);
-
- if (to + nr_copy <= vq->size) {
- rte_memcpy(&vq->used->ring[to],
- &vq->async_descs_split[from],
- nr_copy *
- sizeof(struct vring_used_elem));
- } else {
- uint16_t size = vq->size - to;
-
- rte_memcpy(&vq->used->ring[to],
- &vq->async_descs_split[from],
- size *
- sizeof(struct vring_used_elem));
- rte_memcpy(vq->used->ring,
- &vq->async_descs_split[from +
- size], (nr_copy - size) *
- sizeof(struct vring_used_elem));
- }
+ if (vq->shadow_used_packed[i].len)
+ flags = VRING_DESC_F_WRITE;
+ else
+ flags = 0;
- vq->last_async_desc_idx += nr_copy;
- vq->last_used_idx += nr_copy;
- nr_left -= nr_copy;
- } while (nr_left > 0);
+ if (vq->used_wrap_counter) {
+ flags |= VRING_DESC_F_USED;
+ flags |= VRING_DESC_F_AVAIL;
+ } else {
+ flags &= ~VRING_DESC_F_USED;
+ flags &= ~VRING_DESC_F_AVAIL;
+ }
- __atomic_add_fetch(&vq->used->idx, n_descs, __ATOMIC_RELEASE);
- vhost_vring_call_split(dev, vq);
- } else
- vq->last_async_desc_idx += n_descs;
+ if (i > 0) {
+ vq->desc_packed[vq->last_used_idx].flags = flags;
+ } else {
+ head_idx = vq->last_used_idx;
+ head_flags = flags;
+ }
-done:
- rte_spinlock_unlock(&vq->access_lock);
+ vq_inc_last_used_packed(vq, shadow_ring[i].count);
+ }
- return n_pkts_put;
+ vq->desc_packed[head_idx].flags = head_flags;
}
-static __rte_always_inline uint32_t
-virtio_dev_rx_async_submit(struct virtio_net *dev, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count,
- struct rte_mbuf **comp_pkts, uint32_t *comp_count)
+static __rte_always_inline int
+vhost_enqueue_async_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf *pkt,
+ struct buf_vector *buf_vec,
+ uint16_t *nr_descs,
+ uint16_t *nr_buffers,
+ struct vring_packed_desc *async_descs,
+ struct iovec *src_iovec, struct iovec *dst_iovec,
+ struct rte_vhost_iov_iter *src_it,
+ struct rte_vhost_iov_iter *dst_it)
{
- struct vhost_virtqueue *vq;
- uint32_t nb_tx = 0;
-
- VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
+ uint16_t nr_vec = 0;
+ uint16_t avail_idx = vq->last_avail_idx;
+ uint16_t max_tries, tries = 0;
+ uint16_t buf_id = 0;
+ uint32_t len = 0;
+ uint16_t desc_count = 0;
+ uint32_t size = pkt->pkt_len + sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ uint32_t buffer_len[vq->size];
+ uint16_t buffer_buf_id[vq->size];
+ uint16_t buffer_desc_count[vq->size];
+
+ if (rxvq_is_mergeable(dev))
+ max_tries = vq->size - 1;
+ else
+ max_tries = 1;
+
+ while (size > 0) {
+ /*
+ * if we tried all available ring items, and still
+ * can't get enough buf, it means something abnormal
+ * happened.
+ */
+ if (unlikely(++tries > max_tries))
+ return -1;
+
+ if (unlikely(fill_vec_buf_packed(dev, vq, avail_idx, &desc_count, buf_vec, &nr_vec,
+ &buf_id, &len, VHOST_ACCESS_RW) < 0))
+ return -1;
+
+ len = RTE_MIN(len, size);
+ size -= len;
+
+ buffer_len[*nr_buffers] = len;
+ buffer_buf_id[*nr_buffers] = buf_id;
+ buffer_desc_count[*nr_buffers] = desc_count;
+ *nr_buffers += 1;
+
+ *nr_descs += desc_count;
+ avail_idx += desc_count;
+ if (avail_idx >= vq->size)
+ avail_idx -= vq->size;
+ }
+
+ if (async_mbuf_to_desc(dev, vq, pkt, buf_vec, nr_vec, *nr_buffers, src_iovec, dst_iovec,
+ src_it, dst_it) < 0)
+ return -1;
+ /* store descriptors for DMA */
+ if (avail_idx >= *nr_descs) {
+ rte_memcpy(async_descs, &vq->desc_packed[vq->last_avail_idx],
+ *nr_descs * sizeof(struct vring_packed_desc));
+ } else {
+ uint16_t nr_copy = vq->size - vq->last_avail_idx;
+
+ rte_memcpy(async_descs, &vq->desc_packed[vq->last_avail_idx],
+ nr_copy * sizeof(struct vring_packed_desc));
+ rte_memcpy(async_descs + nr_copy, vq->desc_packed,
+ (*nr_descs - nr_copy) * sizeof(struct vring_packed_desc));
+ }
+
+ vhost_shadow_enqueue_packed(vq, buffer_len, buffer_buf_id, buffer_desc_count, *nr_buffers);
+
+ return 0;
+}
+
+static __rte_always_inline int16_t
+virtio_dev_rx_async_single_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mbuf *pkt, uint16_t *nr_descs, uint16_t *nr_buffers,
+ struct vring_packed_desc *async_descs,
+ struct iovec *src_iovec, struct iovec *dst_iovec,
+ struct rte_vhost_iov_iter *src_it, struct rte_vhost_iov_iter *dst_it)
+{
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+
+ if (unlikely(vhost_enqueue_async_single_packed(dev, vq, pkt, buf_vec, nr_descs, nr_buffers,
+ async_descs, src_iovec, dst_iovec,
+ src_it, dst_it) < 0)) {
+ VHOST_LOG_DATA(DEBUG, "(%d) failed to get enough desc from vring\n", dev->vid);
+ return -1;
+ }
+
+ VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
+ dev->vid, vq->last_avail_idx, vq->last_avail_idx + *nr_descs);
+
+ return 0;
+}
+
+static __rte_always_inline void
+dma_error_handler_packed(struct vhost_virtqueue *vq, struct vring_packed_desc *async_descs,
+ uint16_t async_descs_idx, uint16_t slot_idx, uint32_t nr_err,
+ uint32_t *pkt_idx, uint32_t *num_async_pkts, uint32_t *num_done_pkts)
+{
+ uint16_t descs_err = 0;
+ uint16_t buffers_err = 0;
+ struct async_inflight_info *pkts_info = vq->async_pkts_info;
+
+ *num_async_pkts -= nr_err;
+ *pkt_idx -= nr_err;
+ /* calculate the sum of buffers and descs of DMA-error packets. */
+ while (nr_err-- > 0) {
+ descs_err += pkts_info[slot_idx % vq->size].descs;
+ buffers_err += pkts_info[slot_idx % vq->size].nr_buffers;
+ slot_idx--;
+ }
+
+ vq->async_buffer_idx_packed -= buffers_err;
+
+ if (vq->last_avail_idx >= descs_err) {
+ vq->last_avail_idx -= descs_err;
+
+ rte_memcpy(&vq->desc_packed[vq->last_avail_idx],
+ &async_descs[async_descs_idx - descs_err],
+ descs_err * sizeof(struct vring_packed_desc));
+ } else {
+ uint16_t nr_copy;
+
+ vq->last_avail_idx = vq->last_avail_idx + vq->size - descs_err;
+ nr_copy = vq->size - vq->last_avail_idx;
+ rte_memcpy(&vq->desc_packed[vq->last_avail_idx],
+ &async_descs[async_descs_idx - descs_err],
+ nr_copy * sizeof(struct vring_packed_desc));
+ descs_err -= nr_copy;
+ rte_memcpy(&vq->desc_packed[0], &async_descs[async_descs_idx - descs_err],
+ descs_err * sizeof(struct vring_packed_desc));
+ vq->avail_wrap_counter ^= 1;
+ }
+
+ *num_done_pkts = *pkt_idx - *num_async_pkts;
+}
+
+static __rte_noinline uint32_t
+virtio_dev_rx_async_submit_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint32_t count,
+ struct rte_mbuf **comp_pkts, uint32_t *comp_count)
+{
+ uint32_t pkt_idx = 0, pkt_burst_idx = 0;
+ uint32_t remained = count;
+ uint16_t async_descs_idx = 0;
+ uint16_t num_buffers;
+ uint16_t num_descs;
+ int32_t n_xfer;
+
+ struct rte_vhost_iov_iter *it_pool = vq->it_pool;
+ struct iovec *vec_pool = vq->vec_pool;
+ struct rte_vhost_async_desc tdes[MAX_PKT_BURST];
+ struct iovec *src_iovec = vec_pool;
+ struct iovec *dst_iovec = vec_pool + (VHOST_MAX_ASYNC_VEC >> 1);
+ uint16_t slot_idx = 0;
+ uint16_t segs_await = 0;
+ uint16_t iovec_idx = 0, it_idx = 0;
+ struct async_inflight_info *pkts_info = vq->async_pkts_info;
+ uint32_t n_pkts = 0, pkt_err = 0;
+ uint32_t num_async_pkts = 0, num_done_pkts = 0;
+ struct vring_packed_desc async_descs[vq->size];
+
+ do {
+ rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
+ if (remained >= PACKED_BATCH_SIZE) {
+ if (!virtio_dev_rx_async_batch_packed(dev, vq,
+ &pkts[pkt_idx], comp_pkts, &num_done_pkts)) {
+ pkt_idx += PACKED_BATCH_SIZE;
+ remained -= PACKED_BATCH_SIZE;
+ continue;
+ }
+ }
+
+ num_buffers = 0;
+ num_descs = 0;
+ if (unlikely(virtio_dev_rx_async_single_packed(dev, vq, pkts[pkt_idx],
+ &num_descs, &num_buffers,
+ &async_descs[async_descs_idx],
+ &src_iovec[iovec_idx], &dst_iovec[iovec_idx],
+ &it_pool[it_idx], &it_pool[it_idx + 1]) < 0))
+ break;
+
+ VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
+ dev->vid, vq->last_avail_idx,
+ vq->last_avail_idx + num_descs);
+
+ slot_idx = (vq->async_pkts_idx + num_async_pkts) % vq->size;
+ if (it_pool[it_idx].count) {
+ uint16_t from;
+
+ async_descs_idx += num_descs;
+ async_fill_desc(&tdes[pkt_burst_idx++],
+ &it_pool[it_idx], &it_pool[it_idx + 1]);
+ pkts_info[slot_idx].descs = num_descs;
+ pkts_info[slot_idx].nr_buffers = num_buffers;
+ pkts_info[slot_idx].mbuf = pkts[pkt_idx];
+ num_async_pkts++;
+ iovec_idx += it_pool[it_idx].nr_segs;
+ it_idx += 2;
+
+ segs_await += it_pool[it_idx].nr_segs;
+
+ /**
+ * recover shadow used ring and keep DMA-occupied
+ * descriptors.
+ */
+ from = vq->shadow_used_idx - num_buffers;
+ store_dma_desc_info_packed(vq->shadow_used_packed,
+ vq->async_buffers_packed, vq->size, from,
+ vq->async_buffer_idx_packed, num_buffers);
+
+ vq->async_buffer_idx_packed += num_buffers;
+ if (vq->async_buffer_idx_packed >= vq->size)
+ vq->async_buffer_idx_packed -= vq->size;
+ vq->shadow_used_idx -= num_buffers;
+ } else {
+ comp_pkts[num_done_pkts++] = pkts[pkt_idx];
+ }
+
+ pkt_idx++;
+ remained--;
+ vq_inc_last_avail_packed(vq, num_descs);
+
+ /*
+ * conditions to trigger async device transfer:
+ * - buffered packet number reaches transfer threshold
+ * - unused async iov number is less than max vhost vector
+ */
+ if (unlikely(pkt_burst_idx >= VHOST_ASYNC_BATCH_THRESHOLD ||
+ ((VHOST_MAX_ASYNC_VEC >> 1) - segs_await < BUF_VECTOR_MAX))) {
+ n_xfer = vq->async_ops.transfer_data(dev->vid,
+ queue_id, tdes, 0, pkt_burst_idx);
+ if (n_xfer >= 0) {
+ n_pkts = n_xfer;
+ } else {
+ VHOST_LOG_DATA(ERR,
+ "(%d) %s: failed to transfer data for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ n_pkts = 0;
+ }
+
+ iovec_idx = 0;
+ it_idx = 0;
+ segs_await = 0;
+ vq->async_pkts_inflight_n += n_pkts;
+
+ if (unlikely(n_pkts < pkt_burst_idx)) {
+ /*
+ * log error packets number here and do actual
+ * error processing when applications poll
+ * completion
+ */
+ pkt_err = pkt_burst_idx - n_pkts;
+ pkt_burst_idx = 0;
+ break;
+ }
+
+ pkt_burst_idx = 0;
+ }
+ } while (pkt_idx < count);
+
+ if (pkt_burst_idx) {
+ n_xfer = vq->async_ops.transfer_data(dev->vid, queue_id, tdes, 0, pkt_burst_idx);
+ if (n_xfer >= 0) {
+ n_pkts = n_xfer;
+ } else {
+ VHOST_LOG_DATA(ERR, "(%d) %s: failed to transfer data for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ n_pkts = 0;
+ }
+
+ vq->async_pkts_inflight_n += n_pkts;
+
+ if (unlikely(n_pkts < pkt_burst_idx))
+ pkt_err = pkt_burst_idx - n_pkts;
+ }
+
+ do_data_copy_enqueue(dev, vq);
+
+ if (unlikely(pkt_err))
+ dma_error_handler_packed(vq, async_descs, async_descs_idx, slot_idx, pkt_err,
+ &pkt_idx, &num_async_pkts, &num_done_pkts);
+ vq->async_pkts_idx += num_async_pkts;
+ if (vq->async_pkts_idx >= vq->size)
+ vq->async_pkts_idx -= vq->size;
+ *comp_count = num_done_pkts;
+
+ if (likely(vq->shadow_used_idx)) {
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ vhost_vring_call_packed(dev, vq);
+ }
+
+ return pkt_idx;
+}
+
+static __rte_always_inline void
+write_back_completed_descs_split(struct vhost_virtqueue *vq, uint16_t n_descs)
+{
+ uint16_t nr_left = n_descs;
+ uint16_t nr_copy;
+ uint16_t to, from;
+
+ do {
+ from = vq->last_async_desc_idx_split & (vq->size - 1);
+ nr_copy = nr_left + from <= vq->size ? nr_left : vq->size - from;
+ to = vq->last_used_idx & (vq->size - 1);
+
+ if (to + nr_copy <= vq->size) {
+ rte_memcpy(&vq->used->ring[to], &vq->async_descs_split[from],
+ nr_copy * sizeof(struct vring_used_elem));
+ } else {
+ uint16_t size = vq->size - to;
+
+ rte_memcpy(&vq->used->ring[to], &vq->async_descs_split[from],
+ size * sizeof(struct vring_used_elem));
+ rte_memcpy(&vq->used->ring[0], &vq->async_descs_split[from + size],
+ (nr_copy - size) * sizeof(struct vring_used_elem));
+ }
+
+ vq->last_async_desc_idx_split += nr_copy;
+ vq->last_used_idx += nr_copy;
+ nr_left -= nr_copy;
+ } while (nr_left > 0);
+}
+
+static __rte_always_inline void
+write_back_completed_descs_packed(struct vhost_virtqueue *vq,
+ uint16_t n_buffers)
+{
+ uint16_t nr_left = n_buffers;
+ uint16_t from, to;
+
+ do {
+ from = vq->last_async_buffer_idx_packed;
+ to = (from + nr_left) % vq->size;
+ if (to > from) {
+ vhost_update_used_packed(vq, vq->async_buffers_packed + from, to - from);
+ vq->last_async_buffer_idx_packed += nr_left;
+ nr_left = 0;
+ } else {
+ vhost_update_used_packed(vq, vq->async_buffers_packed + from,
+ vq->size - from);
+ vq->last_async_buffer_idx_packed = 0;
+ nr_left -= vq->size - from;
+ }
+ } while (nr_left > 0);
+}
+
+static __rte_always_inline uint16_t
+vhost_poll_enqueue_completed(struct virtio_net *dev, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ struct vhost_virtqueue *vq;
+ uint16_t n_pkts_cpl = 0, n_pkts_put = 0, n_descs = 0, n_buffers = 0;
+ uint16_t start_idx, pkts_idx, vq_size;
+ struct async_inflight_info *pkts_info;
+ uint16_t from, i;
+ int32_t n_cpl;
+
+ vq = dev->virtqueue[queue_id];
+
+ pkts_idx = vq->async_pkts_idx % vq->size;
+ pkts_info = vq->async_pkts_info;
+ vq_size = vq->size;
+ start_idx = virtio_dev_rx_async_get_info_idx(pkts_idx,
+ vq_size, vq->async_pkts_inflight_n);
+
+ if (count > vq->async_last_pkts_n) {
+ n_cpl = vq->async_ops.check_completed_copies(dev->vid,
+ queue_id, 0, count - vq->async_last_pkts_n);
+ if (n_cpl >= 0) {
+ n_pkts_cpl = n_cpl;
+ } else {
+ VHOST_LOG_DATA(ERR,
+ "(%d) %s: failed to check completed copies for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ n_pkts_cpl = 0;
+ }
+ }
+ n_pkts_cpl += vq->async_last_pkts_n;
+
+ n_pkts_put = RTE_MIN(count, n_pkts_cpl);
+ if (unlikely(n_pkts_put == 0)) {
+ vq->async_last_pkts_n = n_pkts_cpl;
+ return 0;
+ }
+
+ if (vq_is_packed(dev)) {
+ for (i = 0; i < n_pkts_put; i++) {
+ from = (start_idx + i) % vq_size;
+ n_buffers += pkts_info[from].nr_buffers;
+ pkts[i] = pkts_info[from].mbuf;
+ }
+ } else {
+ for (i = 0; i < n_pkts_put; i++) {
+ from = (start_idx + i) & (vq_size - 1);
+ n_descs += pkts_info[from].descs;
+ pkts[i] = pkts_info[from].mbuf;
+ }
+ }
+
+ vq->async_last_pkts_n = n_pkts_cpl - n_pkts_put;
+ vq->async_pkts_inflight_n -= n_pkts_put;
+
+ if (likely(vq->enabled && vq->access_ok)) {
+ if (vq_is_packed(dev)) {
+ write_back_completed_descs_packed(vq, n_buffers);
+
+ vhost_vring_call_packed(dev, vq);
+ } else {
+ write_back_completed_descs_split(vq, n_descs);
+
+ __atomic_add_fetch(&vq->used->idx, n_descs,
+ __ATOMIC_RELEASE);
+ vhost_vring_call_split(dev, vq);
+ }
+ } else {
+ if (vq_is_packed(dev)) {
+ vq->last_async_buffer_idx_packed += n_buffers;
+ if (vq->last_async_buffer_idx_packed >= vq->size)
+ vq->last_async_buffer_idx_packed -= vq->size;
+ } else {
+ vq->last_async_desc_idx_split += n_descs;
+ }
+ }
+
+ return n_pkts_put;
+}
+
+uint16_t
+rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ struct virtio_net *dev = get_device(vid);
+ struct vhost_virtqueue *vq;
+ uint16_t n_pkts_cpl = 0;
+
+ if (!dev)
+ return 0;
+
+ VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
+ VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
+ dev->vid, __func__, queue_id);
+ return 0;
+ }
+
+ vq = dev->virtqueue[queue_id];
+
+ if (unlikely(!vq->async_registered)) {
+ VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ return 0;
+ }
+
+ rte_spinlock_lock(&vq->access_lock);
+
+ n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+
+ rte_spinlock_unlock(&vq->access_lock);
+
+ return n_pkts_cpl;
+}
+
+uint16_t
+rte_vhost_clear_queue_thread_unsafe(int vid, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ struct virtio_net *dev = get_device(vid);
+ struct vhost_virtqueue *vq;
+ uint16_t n_pkts_cpl = 0;
+
+ if (!dev)
+ return 0;
+
+ VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
+ VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
+ dev->vid, __func__, queue_id);
+ return 0;
+ }
+
+ vq = dev->virtqueue[queue_id];
+
+ if (unlikely(!vq->async_registered)) {
+ VHOST_LOG_DATA(ERR, "(%d) %s: async not registered for queue id %d.\n",
+ dev->vid, __func__, queue_id);
+ return 0;
+ }
+
+ n_pkts_cpl = vhost_poll_enqueue_completed(dev, queue_id, pkts, count);
+
+ return n_pkts_cpl;
+}
+
+static __rte_always_inline uint32_t
+virtio_dev_rx_async_submit(struct virtio_net *dev, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint32_t count,
+ struct rte_mbuf **comp_pkts, uint32_t *comp_count)
+{
+ struct vhost_virtqueue *vq;
+ uint32_t nb_tx = 0;
+
+ VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
+ VHOST_LOG_DATA(ERR, "(%d) %s: invalid virtqueue idx %d.\n",
+ dev->vid, __func__, queue_id);
return 0;
}
if (count == 0)
goto out;
- /* TODO: packed queue not implemented */
if (vq_is_packed(dev))
- nb_tx = 0;
+ nb_tx = virtio_dev_rx_async_submit_packed(dev,
+ vq, queue_id, pkts, count, comp_pkts,
+ comp_count);
else
nb_tx = virtio_dev_rx_async_submit_split(dev,
vq, queue_id, pkts, count, comp_pkts,
return false;
}
-static void
-parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr)
+static int
+parse_headers(struct rte_mbuf *m, uint8_t *l4_proto)
{
struct rte_ipv4_hdr *ipv4_hdr;
struct rte_ipv6_hdr *ipv6_hdr;
- void *l3_hdr = NULL;
struct rte_ether_hdr *eth_hdr;
uint16_t ethertype;
+ uint16_t data_len = rte_pktmbuf_data_len(m);
+
+ if (data_len < sizeof(struct rte_ether_hdr))
+ return -EINVAL;
eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
ethertype = rte_be_to_cpu_16(eth_hdr->ether_type);
if (ethertype == RTE_ETHER_TYPE_VLAN) {
+ if (data_len < sizeof(struct rte_ether_hdr) +
+ sizeof(struct rte_vlan_hdr))
+ goto error;
+
struct rte_vlan_hdr *vlan_hdr =
(struct rte_vlan_hdr *)(eth_hdr + 1);
ethertype = rte_be_to_cpu_16(vlan_hdr->eth_proto);
}
- l3_hdr = (char *)eth_hdr + m->l2_len;
-
switch (ethertype) {
case RTE_ETHER_TYPE_IPV4:
- ipv4_hdr = l3_hdr;
- *l4_proto = ipv4_hdr->next_proto_id;
+ if (data_len < m->l2_len + sizeof(struct rte_ipv4_hdr))
+ goto error;
+ ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct rte_ipv4_hdr *,
+ m->l2_len);
m->l3_len = rte_ipv4_hdr_len(ipv4_hdr);
- *l4_hdr = (char *)l3_hdr + m->l3_len;
+ if (data_len < m->l2_len + m->l3_len)
+ goto error;
m->ol_flags |= PKT_TX_IPV4;
+ *l4_proto = ipv4_hdr->next_proto_id;
break;
case RTE_ETHER_TYPE_IPV6:
- ipv6_hdr = l3_hdr;
- *l4_proto = ipv6_hdr->proto;
+ if (data_len < m->l2_len + sizeof(struct rte_ipv6_hdr))
+ goto error;
+ ipv6_hdr = rte_pktmbuf_mtod_offset(m, struct rte_ipv6_hdr *,
+ m->l2_len);
m->l3_len = sizeof(struct rte_ipv6_hdr);
- *l4_hdr = (char *)l3_hdr + m->l3_len;
m->ol_flags |= PKT_TX_IPV6;
+ *l4_proto = ipv6_hdr->proto;
break;
default:
- m->l3_len = 0;
- *l4_proto = 0;
- *l4_hdr = NULL;
+ /* a valid L3 header is needed for further L4 parsing */
+ goto error;
+ }
+
+ /* both CSUM and GSO need a valid L4 header */
+ switch (*l4_proto) {
+ case IPPROTO_TCP:
+ if (data_len < m->l2_len + m->l3_len +
+ sizeof(struct rte_tcp_hdr))
+ goto error;
break;
+ case IPPROTO_UDP:
+ if (data_len < m->l2_len + m->l3_len +
+ sizeof(struct rte_udp_hdr))
+ goto error;
+ break;
+ case IPPROTO_SCTP:
+ if (data_len < m->l2_len + m->l3_len +
+ sizeof(struct rte_sctp_hdr))
+ goto error;
+ break;
+ default:
+ goto error;
}
+
+ return 0;
+
+error:
+ m->l2_len = 0;
+ m->l3_len = 0;
+ m->ol_flags = 0;
+ return -EINVAL;
}
static __rte_always_inline void
-vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
+vhost_dequeue_offload_legacy(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
{
- uint16_t l4_proto = 0;
- void *l4_hdr = NULL;
+ uint8_t l4_proto = 0;
struct rte_tcp_hdr *tcp_hdr = NULL;
+ uint16_t tcp_len;
+ uint16_t data_len = rte_pktmbuf_data_len(m);
- if (hdr->flags == 0 && hdr->gso_type == VIRTIO_NET_HDR_GSO_NONE)
+ if (parse_headers(m, &l4_proto) < 0)
return;
- parse_ethernet(m, &l4_proto, &l4_hdr);
if (hdr->flags == VIRTIO_NET_HDR_F_NEEDS_CSUM) {
if (hdr->csum_start == (m->l2_len + m->l3_len)) {
switch (hdr->csum_offset) {
case (offsetof(struct rte_tcp_hdr, cksum)):
- if (l4_proto == IPPROTO_TCP)
- m->ol_flags |= PKT_TX_TCP_CKSUM;
+ if (l4_proto != IPPROTO_TCP)
+ goto error;
+ m->ol_flags |= PKT_TX_TCP_CKSUM;
break;
case (offsetof(struct rte_udp_hdr, dgram_cksum)):
- if (l4_proto == IPPROTO_UDP)
- m->ol_flags |= PKT_TX_UDP_CKSUM;
+ if (l4_proto != IPPROTO_UDP)
+ goto error;
+ m->ol_flags |= PKT_TX_UDP_CKSUM;
break;
case (offsetof(struct rte_sctp_hdr, cksum)):
- if (l4_proto == IPPROTO_SCTP)
- m->ol_flags |= PKT_TX_SCTP_CKSUM;
+ if (l4_proto != IPPROTO_SCTP)
+ goto error;
+ m->ol_flags |= PKT_TX_SCTP_CKSUM;
break;
default:
- break;
+ goto error;
}
+ } else {
+ goto error;
}
}
- if (l4_hdr && hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
case VIRTIO_NET_HDR_GSO_TCPV4:
case VIRTIO_NET_HDR_GSO_TCPV6:
- tcp_hdr = l4_hdr;
+ if (l4_proto != IPPROTO_TCP)
+ goto error;
+ tcp_hdr = rte_pktmbuf_mtod_offset(m,
+ struct rte_tcp_hdr *,
+ m->l2_len + m->l3_len);
+ tcp_len = (tcp_hdr->data_off & 0xf0) >> 2;
+ if (data_len < m->l2_len + m->l3_len + tcp_len)
+ goto error;
m->ol_flags |= PKT_TX_TCP_SEG;
m->tso_segsz = hdr->gso_size;
- m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
+ m->l4_len = tcp_len;
break;
case VIRTIO_NET_HDR_GSO_UDP:
+ if (l4_proto != IPPROTO_UDP)
+ goto error;
m->ol_flags |= PKT_TX_UDP_SEG;
m->tso_segsz = hdr->gso_size;
m->l4_len = sizeof(struct rte_udp_hdr);
default:
VHOST_LOG_DATA(WARNING,
"unsupported gso type %u.\n", hdr->gso_type);
+ goto error;
+ }
+ }
+ return;
+
+error:
+ m->l2_len = 0;
+ m->l3_len = 0;
+ m->ol_flags = 0;
+}
+
+static __rte_always_inline void
+vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m,
+ bool legacy_ol_flags)
+{
+ struct rte_net_hdr_lens hdr_lens;
+ int l4_supported = 0;
+ uint32_t ptype;
+
+ if (hdr->flags == 0 && hdr->gso_type == VIRTIO_NET_HDR_GSO_NONE)
+ return;
+
+ if (legacy_ol_flags) {
+ vhost_dequeue_offload_legacy(hdr, m);
+ return;
+ }
+
+ m->ol_flags |= PKT_RX_IP_CKSUM_UNKNOWN;
+
+ ptype = rte_net_get_ptype(m, &hdr_lens, RTE_PTYPE_ALL_MASK);
+ m->packet_type = ptype;
+ if ((ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_TCP ||
+ (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_UDP ||
+ (ptype & RTE_PTYPE_L4_MASK) == RTE_PTYPE_L4_SCTP)
+ l4_supported = 1;
+
+ /* According to Virtio 1.1 spec, the device only needs to look at
+ * VIRTIO_NET_HDR_F_NEEDS_CSUM in the packet transmission path.
+ * This differs from the processing incoming packets path where the
+ * driver could rely on VIRTIO_NET_HDR_F_DATA_VALID flag set by the
+ * device.
+ *
+ * 5.1.6.2.1 Driver Requirements: Packet Transmission
+ * The driver MUST NOT set the VIRTIO_NET_HDR_F_DATA_VALID and
+ * VIRTIO_NET_HDR_F_RSC_INFO bits in flags.
+ *
+ * 5.1.6.2.2 Device Requirements: Packet Transmission
+ * The device MUST ignore flag bits that it does not recognize.
+ */
+ if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+ uint32_t hdrlen;
+
+ hdrlen = hdr_lens.l2_len + hdr_lens.l3_len + hdr_lens.l4_len;
+ if (hdr->csum_start <= hdrlen && l4_supported != 0) {
+ m->ol_flags |= PKT_RX_L4_CKSUM_NONE;
+ } else {
+ /* Unknown proto or tunnel, do sw cksum. We can assume
+ * the cksum field is in the first segment since the
+ * buffers we provided to the host are large enough.
+ * In case of SCTP, this will be wrong since it's a CRC
+ * but there's nothing we can do.
+ */
+ uint16_t csum = 0, off;
+
+ if (rte_raw_cksum_mbuf(m, hdr->csum_start,
+ rte_pktmbuf_pkt_len(m) - hdr->csum_start, &csum) < 0)
+ return;
+ if (likely(csum != 0xffff))
+ csum = ~csum;
+ off = hdr->csum_offset + hdr->csum_start;
+ if (rte_pktmbuf_data_len(m) >= off + 1)
+ *rte_pktmbuf_mtod_offset(m, uint16_t *, off) = csum;
+ }
+ }
+
+ if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ if (hdr->gso_size == 0)
+ return;
+
+ switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+ case VIRTIO_NET_HDR_GSO_TCPV4:
+ case VIRTIO_NET_HDR_GSO_TCPV6:
+ if ((ptype & RTE_PTYPE_L4_MASK) != RTE_PTYPE_L4_TCP)
+ break;
+ m->ol_flags |= PKT_RX_LRO | PKT_RX_L4_CKSUM_NONE;
+ m->tso_segsz = hdr->gso_size;
+ break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ if ((ptype & RTE_PTYPE_L4_MASK) != RTE_PTYPE_L4_UDP)
+ break;
+ m->ol_flags |= PKT_RX_LRO | PKT_RX_L4_CKSUM_NONE;
+ m->tso_segsz = hdr->gso_size;
+ break;
+ default:
break;
}
}
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,
- struct rte_mbuf *m, struct rte_mempool *mbuf_pool)
+ struct rte_mbuf *m, struct rte_mempool *mbuf_pool,
+ bool legacy_ol_flags)
{
uint32_t buf_avail, buf_offset;
uint64_t buf_addr, buf_len;
m->pkt_len += mbuf_offset;
if (hdr)
- vhost_dequeue_offload(hdr, m);
+ vhost_dequeue_offload(hdr, m, legacy_ol_flags);
out:
}
/*
- * Allocate a host supported pktmbuf.
+ * Prepare a host supported pktmbuf.
*/
-static __rte_always_inline struct rte_mbuf *
-virtio_dev_pktmbuf_alloc(struct virtio_net *dev, struct rte_mempool *mp,
+static __rte_always_inline int
+virtio_dev_pktmbuf_prep(struct virtio_net *dev, struct rte_mbuf *pkt,
uint32_t data_len)
{
- struct rte_mbuf *pkt = rte_pktmbuf_alloc(mp);
-
- if (unlikely(pkt == NULL)) {
- VHOST_LOG_DATA(ERR,
- "Failed to allocate memory for mbuf.\n");
- return NULL;
- }
-
if (rte_pktmbuf_tailroom(pkt) >= data_len)
- return pkt;
+ return 0;
/* attach an external buffer if supported */
if (dev->extbuf && !virtio_dev_extbuf_alloc(pkt, data_len))
- return pkt;
+ return 0;
/* check if chained buffers are allowed */
if (!dev->linearbuf)
- return pkt;
-
- /* Data doesn't fit into the buffer and the host supports
- * only linear buffers
- */
- rte_pktmbuf_free(pkt);
+ return 0;
- return NULL;
+ return -1;
}
-static __rte_noinline uint16_t
+__rte_always_inline
+static 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)
+ struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count,
+ bool legacy_ol_flags)
{
uint16_t i;
uint16_t free_entries;
VHOST_LOG_DATA(DEBUG, "(%d) about to dequeue %u buffers\n",
dev->vid, count);
+ if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, count))
+ return 0;
+
for (i = 0; i < count; i++) {
struct buf_vector buf_vec[BUF_VECTOR_MAX];
uint16_t head_idx;
update_shadow_used_ring_split(vq, head_idx, 0);
- pkts[i] = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
- if (unlikely(pkts[i] == NULL)) {
+ err = virtio_dev_pktmbuf_prep(dev, pkts[i], buf_len);
+ if (unlikely(err)) {
/*
* mbuf allocation fails for jumbo packets when external
* buffer allocation is not allowed and linear buffer
}
err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
- mbuf_pool);
+ mbuf_pool, legacy_ol_flags);
if (unlikely(err)) {
- rte_pktmbuf_free(pkts[i]);
if (!allocerr_warned) {
VHOST_LOG_DATA(ERR,
"Failed to copy desc to mbuf on %s.\n",
}
}
+ if (dropped)
+ rte_pktmbuf_free_bulk(&pkts[i - 1], count - i + 1);
+
vq->last_avail_idx += i;
do_data_copy_dequeue(vq);
return (i - dropped);
}
+__rte_noinline
+static uint16_t
+virtio_dev_tx_split_legacy(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, true);
+}
+
+__rte_noinline
+static uint16_t
+virtio_dev_tx_split_compliant(struct virtio_net *dev,
+ struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ return virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count, false);
+}
+
static __rte_always_inline int
vhost_reserve_avail_batch_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
- struct rte_mempool *mbuf_pool,
struct rte_mbuf **pkts,
uint16_t avail_idx,
uintptr_t *desc_addrs,
}
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
- pkts[i] = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, lens[i]);
- if (!pkts[i])
- goto free_buf;
+ if (virtio_dev_pktmbuf_prep(dev, pkts[i], lens[i]))
+ goto err;
}
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
if (unlikely(buf_lens[i] < (lens[i] - buf_offset)))
- goto free_buf;
+ goto err;
}
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
return 0;
-free_buf:
- for (i = 0; i < PACKED_BATCH_SIZE; i++)
- rte_pktmbuf_free(pkts[i]);
-
+err:
return -1;
}
static __rte_always_inline int
virtio_dev_tx_batch_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
- struct rte_mempool *mbuf_pool,
- struct rte_mbuf **pkts)
+ struct rte_mbuf **pkts,
+ bool legacy_ol_flags)
{
uint16_t avail_idx = vq->last_avail_idx;
uint32_t buf_offset = sizeof(struct virtio_net_hdr_mrg_rxbuf);
uint16_t ids[PACKED_BATCH_SIZE];
uint16_t i;
- if (vhost_reserve_avail_batch_packed(dev, vq, mbuf_pool, pkts,
- avail_idx, desc_addrs, ids))
+ if (vhost_reserve_avail_batch_packed(dev, vq, pkts, avail_idx,
+ desc_addrs, ids))
return -1;
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
if (virtio_net_with_host_offload(dev)) {
vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
hdr = (struct virtio_net_hdr *)(desc_addrs[i]);
- vhost_dequeue_offload(hdr, pkts[i]);
+ vhost_dequeue_offload(hdr, pkts[i], legacy_ol_flags);
}
}
vhost_dequeue_single_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
struct rte_mempool *mbuf_pool,
- struct rte_mbuf **pkts,
+ struct rte_mbuf *pkts,
uint16_t *buf_id,
- uint16_t *desc_count)
+ uint16_t *desc_count,
+ bool legacy_ol_flags)
{
struct buf_vector buf_vec[BUF_VECTOR_MAX];
uint32_t buf_len;
VHOST_ACCESS_RO) < 0))
return -1;
- *pkts = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
- if (unlikely(*pkts == NULL)) {
+ if (unlikely(virtio_dev_pktmbuf_prep(dev, pkts, buf_len))) {
if (!allocerr_warned) {
VHOST_LOG_DATA(ERR,
"Failed mbuf alloc of size %d from %s on %s.\n",
return -1;
}
- err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, *pkts,
- mbuf_pool);
+ err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts,
+ mbuf_pool, legacy_ol_flags);
if (unlikely(err)) {
if (!allocerr_warned) {
VHOST_LOG_DATA(ERR,
dev->ifname);
allocerr_warned = true;
}
- rte_pktmbuf_free(*pkts);
return -1;
}
virtio_dev_tx_single_packed(struct virtio_net *dev,
struct vhost_virtqueue *vq,
struct rte_mempool *mbuf_pool,
- struct rte_mbuf **pkts)
+ struct rte_mbuf *pkts,
+ bool legacy_ol_flags)
{
uint16_t buf_id, desc_count = 0;
int ret;
ret = vhost_dequeue_single_packed(dev, vq, mbuf_pool, pkts, &buf_id,
- &desc_count);
+ &desc_count, legacy_ol_flags);
if (likely(desc_count > 0)) {
if (virtio_net_is_inorder(dev))
return ret;
}
-static __rte_noinline uint16_t
+__rte_always_inline
+static uint16_t
virtio_dev_tx_packed(struct virtio_net *dev,
struct vhost_virtqueue *__rte_restrict vq,
struct rte_mempool *mbuf_pool,
struct rte_mbuf **__rte_restrict pkts,
- uint32_t count)
+ uint32_t count,
+ bool legacy_ol_flags)
{
uint32_t pkt_idx = 0;
- uint32_t remained = count;
+
+ if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, count))
+ return 0;
do {
rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
- if (remained >= PACKED_BATCH_SIZE) {
- if (!virtio_dev_tx_batch_packed(dev, vq, mbuf_pool,
- &pkts[pkt_idx])) {
+ if (count - pkt_idx >= PACKED_BATCH_SIZE) {
+ if (!virtio_dev_tx_batch_packed(dev, vq,
+ &pkts[pkt_idx],
+ legacy_ol_flags)) {
pkt_idx += PACKED_BATCH_SIZE;
- remained -= PACKED_BATCH_SIZE;
continue;
}
}
if (virtio_dev_tx_single_packed(dev, vq, mbuf_pool,
- &pkts[pkt_idx]))
+ pkts[pkt_idx],
+ legacy_ol_flags))
break;
pkt_idx++;
- remained--;
+ } while (pkt_idx < count);
- } while (remained);
+ if (pkt_idx != count)
+ rte_pktmbuf_free_bulk(&pkts[pkt_idx], count - pkt_idx);
if (vq->shadow_used_idx) {
do_data_copy_dequeue(vq);
return pkt_idx;
}
+__rte_noinline
+static uint16_t
+virtio_dev_tx_packed_legacy(struct virtio_net *dev,
+ struct vhost_virtqueue *__rte_restrict vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **__rte_restrict pkts, uint32_t count)
+{
+ return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, true);
+}
+
+__rte_noinline
+static uint16_t
+virtio_dev_tx_packed_compliant(struct virtio_net *dev,
+ struct vhost_virtqueue *__rte_restrict vq, struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **__rte_restrict pkts, uint32_t count)
+{
+ return virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count, false);
+}
+
uint16_t
rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
count -= 1;
}
- if (vq_is_packed(dev))
- count = virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts, count);
- else
- count = virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count);
+ if (vq_is_packed(dev)) {
+ if (dev->flags & VIRTIO_DEV_LEGACY_OL_FLAGS)
+ count = virtio_dev_tx_packed_legacy(dev, vq, mbuf_pool, pkts, count);
+ else
+ count = virtio_dev_tx_packed_compliant(dev, vq, mbuf_pool, pkts, count);
+ } else {
+ if (dev->flags & VIRTIO_DEV_LEGACY_OL_FLAGS)
+ count = virtio_dev_tx_split_legacy(dev, vq, mbuf_pool, pkts, count);
+ else
+ count = virtio_dev_tx_split_compliant(dev, vq, mbuf_pool, pkts, count);
+ }
out:
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))