#include <rte_udp.h>
#include <rte_sctp.h>
#include <rte_arp.h>
+#include <rte_spinlock.h>
+#include <rte_malloc.h>
#include "iotlb.h"
#include "vhost.h"
#define MAX_BATCH_LEN 256
+static __rte_always_inline bool
+rxvq_is_mergeable(struct virtio_net *dev)
+{
+ return dev->features & (1ULL << VIRTIO_NET_F_MRG_RXBUF);
+}
+
+static __rte_always_inline bool
+virtio_net_is_inorder(struct virtio_net *dev)
+{
+ return dev->features & (1ULL << VIRTIO_F_IN_ORDER);
+}
+
static bool
is_valid_virt_queue_idx(uint32_t idx, int is_tx, uint32_t nr_vring)
{
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(struct virtio_net *dev, struct vhost_virtqueue *vq,
- uint16_t to, uint16_t from, uint16_t size)
+do_flush_shadow_used_ring_split(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint16_t to, uint16_t from, uint16_t size)
{
rte_memcpy(&vq->used->ring[to],
- &vq->shadow_used_ring[from],
+ &vq->shadow_used_split[from],
size * sizeof(struct vring_used_elem));
- vhost_log_used_vring(dev, vq,
+ vhost_log_cache_used_vring(dev, vq,
offsetof(struct vring_used, ring[to]),
size * sizeof(struct vring_used_elem));
}
static __rte_always_inline void
-flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq)
+flush_shadow_used_ring_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
{
uint16_t used_idx = vq->last_used_idx & (vq->size - 1);
if (used_idx + vq->shadow_used_idx <= vq->size) {
- do_flush_shadow_used_ring(dev, vq, used_idx, 0,
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0,
vq->shadow_used_idx);
} else {
uint16_t size;
/* update used ring interval [used_idx, vq->size] */
size = vq->size - used_idx;
- do_flush_shadow_used_ring(dev, vq, used_idx, 0, size);
+ do_flush_shadow_used_ring_split(dev, vq, used_idx, 0, size);
/* update the left half used ring interval [0, left_size] */
- do_flush_shadow_used_ring(dev, vq, 0, size,
+ do_flush_shadow_used_ring_split(dev, vq, 0, size,
vq->shadow_used_idx - size);
}
vq->last_used_idx += vq->shadow_used_idx;
- rte_smp_wmb();
+ vhost_log_cache_sync(dev, vq);
- *(volatile uint16_t *)&vq->used->idx += vq->shadow_used_idx;
+ __atomic_add_fetch(&vq->used->idx, vq->shadow_used_idx,
+ __ATOMIC_RELEASE);
+ vq->shadow_used_idx = 0;
vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
sizeof(vq->used->idx));
}
static __rte_always_inline void
-update_shadow_used_ring(struct vhost_virtqueue *vq,
- uint16_t desc_idx, uint16_t len)
+update_shadow_used_ring_split(struct vhost_virtqueue *vq,
+ uint16_t desc_idx, uint32_t len)
{
uint16_t i = vq->shadow_used_idx++;
- vq->shadow_used_ring[i].id = desc_idx;
- vq->shadow_used_ring[i].len = len;
+ vq->shadow_used_split[i].id = desc_idx;
+ vq->shadow_used_split[i].len = len;
}
-static inline void
-do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
+static __rte_always_inline void
+vhost_flush_enqueue_shadow_packed(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;
+ uint16_t used_idx = vq->last_used_idx;
+ uint16_t head_idx = vq->last_used_idx;
+ uint16_t head_flags = 0;
+
+ /* Split loop in two to save memory barriers */
+ for (i = 0; i < vq->shadow_used_idx; i++) {
+ vq->desc_packed[used_idx].id = vq->shadow_used_packed[i].id;
+ vq->desc_packed[used_idx].len = vq->shadow_used_packed[i].len;
+
+ used_idx += vq->shadow_used_packed[i].count;
+ if (used_idx >= vq->size)
+ used_idx -= vq->size;
+ }
- for (i = 0; i < count; i++) {
- rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
- vhost_log_write(dev, elem[i].log_addr, elem[i].len);
- PRINT_PACKET(dev, (uintptr_t)elem[i].dst, elem[i].len, 0);
+ rte_smp_wmb();
+
+ for (i = 0; i < vq->shadow_used_idx; i++) {
+ uint16_t flags;
+
+ if (vq->shadow_used_packed[i].len)
+ flags = VRING_DESC_F_WRITE;
+ else
+ flags = 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;
+ }
+
+ if (i > 0) {
+ vq->desc_packed[vq->last_used_idx].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq,
+ vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+ } else {
+ head_idx = vq->last_used_idx;
+ head_flags = flags;
+ }
+
+ vq_inc_last_used_packed(vq, vq->shadow_used_packed[i].count);
}
+
+ vq->desc_packed[head_idx].flags = head_flags;
+
+ vhost_log_cache_used_vring(dev, vq,
+ head_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+
+ vq->shadow_used_idx = 0;
+ vhost_log_cache_sync(dev, vq);
}
-static inline void
-do_data_copy_dequeue(struct vhost_virtqueue *vq)
+static __rte_always_inline void
+vhost_flush_dequeue_shadow_packed(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;
+ struct vring_used_elem_packed *used_elem = &vq->shadow_used_packed[0];
- for (i = 0; i < count; i++)
- rte_memcpy(elem[i].dst, elem[i].src, elem[i].len);
+ vq->desc_packed[vq->shadow_last_used_idx].id = used_elem->id;
+ rte_smp_wmb();
+ vq->desc_packed[vq->shadow_last_used_idx].flags = used_elem->flags;
+
+ vhost_log_cache_used_vring(dev, vq, vq->shadow_last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc));
+ vq->shadow_used_idx = 0;
+ vhost_log_cache_sync(dev, vq);
+}
+
+static __rte_always_inline void
+vhost_flush_enqueue_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint64_t *lens,
+ uint16_t *ids)
+{
+ 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->desc_packed[vq->last_used_idx + i].id = ids[i];
+ vq->desc_packed[vq->last_used_idx + i].len = lens[i];
+ }
+
+ rte_smp_wmb();
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ vq->desc_packed[vq->last_used_idx + i].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq, vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc) *
+ PACKED_BATCH_SIZE);
+ vhost_log_cache_sync(dev, vq);
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_batch_packed_inorder(struct vhost_virtqueue *vq,
+ uint16_t id)
+{
+ vq->shadow_used_packed[0].id = id;
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].flags =
+ PACKED_DESC_DEQUEUE_USED_FLAG(vq->used_wrap_counter);
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].count = 1;
+ vq->shadow_used_idx++;
+ }
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ uint16_t *ids)
+{
+ uint16_t flags;
+ uint16_t i;
+ uint16_t begin;
+
+ flags = PACKED_DESC_DEQUEUE_USED_FLAG(vq->used_wrap_counter);
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].id = ids[0];
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].count = 1;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ begin = 1;
+ } else
+ begin = 0;
+
+ vhost_for_each_try_unroll(i, begin, PACKED_BATCH_SIZE) {
+ vq->desc_packed[vq->last_used_idx + i].id = ids[i];
+ vq->desc_packed[vq->last_used_idx + i].len = 0;
+ }
+
+ rte_smp_wmb();
+ vhost_for_each_try_unroll(i, begin, PACKED_BATCH_SIZE)
+ vq->desc_packed[vq->last_used_idx + i].flags = flags;
+
+ vhost_log_cache_used_vring(dev, vq, vq->last_used_idx *
+ sizeof(struct vring_packed_desc),
+ sizeof(struct vring_packed_desc) *
+ PACKED_BATCH_SIZE);
+ vhost_log_cache_sync(dev, vq);
+
+ vq_inc_last_used_packed(vq, PACKED_BATCH_SIZE);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_single_packed(struct vhost_virtqueue *vq,
+ uint16_t buf_id,
+ uint16_t count)
+{
+ uint16_t flags;
+
+ flags = vq->desc_packed[vq->last_used_idx].flags;
+ 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;
+ }
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+
+ vq->shadow_used_packed[0].id = buf_id;
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ } else {
+ vq->desc_packed[vq->last_used_idx].id = buf_id;
+ vq->desc_packed[vq->last_used_idx].len = 0;
+ vq->desc_packed[vq->last_used_idx].flags = flags;
+ }
+
+ vq_inc_last_used_packed(vq, count);
+}
+
+static __rte_always_inline void
+vhost_shadow_dequeue_single_packed_inorder(struct vhost_virtqueue *vq,
+ uint16_t buf_id,
+ uint16_t count)
+{
+ uint16_t flags;
+
+ vq->shadow_used_packed[0].id = buf_id;
+
+ flags = vq->desc_packed[vq->last_used_idx].flags;
+ 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;
+ }
+
+ if (!vq->shadow_used_idx) {
+ vq->shadow_last_used_idx = vq->last_used_idx;
+ vq->shadow_used_packed[0].len = 0;
+ vq->shadow_used_packed[0].flags = flags;
+ vq->shadow_used_idx++;
+ }
+
+ vq_inc_last_used_packed(vq, count);
+}
+
+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)
+{
+ 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 = vq->last_used_idx &
+ PACKED_BATCH_MASK;
+ vq->shadow_used_packed[vq->shadow_used_idx].id = id[i];
+ vq->shadow_used_packed[vq->shadow_used_idx].len = len[i];
+ vq->shadow_used_packed[vq->shadow_used_idx].count = count[i];
+ vq->shadow_aligned_idx += count[i];
+ vq->shadow_used_idx++;
+ }
+
+ if (vq->shadow_aligned_idx >= PACKED_BATCH_SIZE) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
}
/* avoid write operation when necessary, to lessen cache issues */
(var) = (val); \
} while (0)
-static void
+static __rte_always_inline void
virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr)
{
uint64_t csum_l4 = m_buf->ol_flags & PKT_TX_L4_MASK;
switch (csum_l4) {
case PKT_TX_TCP_CKSUM:
- net_hdr->csum_offset = (offsetof(struct tcp_hdr,
+ net_hdr->csum_offset = (offsetof(struct rte_tcp_hdr,
cksum));
break;
case PKT_TX_UDP_CKSUM:
- net_hdr->csum_offset = (offsetof(struct udp_hdr,
+ net_hdr->csum_offset = (offsetof(struct rte_udp_hdr,
dgram_cksum));
break;
case PKT_TX_SCTP_CKSUM:
- net_hdr->csum_offset = (offsetof(struct sctp_hdr,
+ net_hdr->csum_offset = (offsetof(struct rte_sctp_hdr,
cksum));
break;
}
/* IP cksum verification cannot be bypassed, then calculate here */
if (m_buf->ol_flags & PKT_TX_IP_CKSUM) {
- struct ipv4_hdr *ipv4_hdr;
+ struct rte_ipv4_hdr *ipv4_hdr;
- ipv4_hdr = rte_pktmbuf_mtod_offset(m_buf, struct ipv4_hdr *,
+ ipv4_hdr = rte_pktmbuf_mtod_offset(m_buf, struct rte_ipv4_hdr *,
m_buf->l2_len);
+ ipv4_hdr->hdr_checksum = 0;
ipv4_hdr->hdr_checksum = rte_ipv4_cksum(ipv4_hdr);
}
net_hdr->gso_size = m_buf->tso_segsz;
net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len
+ m_buf->l4_len;
+ } else if (m_buf->ol_flags & PKT_TX_UDP_SEG) {
+ net_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ net_hdr->gso_size = m_buf->tso_segsz;
+ net_hdr->hdr_len = m_buf->l2_len + m_buf->l3_len +
+ m_buf->l4_len;
} else {
ASSIGN_UNLESS_EQUAL(net_hdr->gso_type, 0);
ASSIGN_UNLESS_EQUAL(net_hdr->gso_size, 0);
}
static __rte_always_inline int
-copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
- struct vring_desc *descs, struct rte_mbuf *m,
- uint16_t desc_idx, uint32_t size)
+map_one_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct buf_vector *buf_vec, uint16_t *vec_idx,
+ uint64_t desc_iova, uint64_t desc_len, uint8_t perm)
{
- uint32_t desc_avail, desc_offset;
- uint32_t mbuf_avail, mbuf_offset;
- uint32_t cpy_len;
- struct vring_desc *desc;
- uint64_t desc_addr;
- /* A counter to avoid desc dead loop chain */
- uint16_t nr_desc = 1;
- struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
- uint16_t copy_nb = vq->batch_copy_nb_elems;
- int error = 0;
-
- desc = &descs[desc_idx];
- desc_addr = vhost_iova_to_vva(dev, vq, desc->addr,
- desc->len, VHOST_ACCESS_RW);
- /*
- * Checking of 'desc_addr' placed outside of 'unlikely' macro to avoid
- * performance issue with some versions of gcc (4.8.4 and 5.3.0) which
- * otherwise stores offset on the stack instead of in a register.
- */
- if (unlikely(desc->len < dev->vhost_hlen) || !desc_addr) {
- error = -1;
- goto out;
- }
-
- rte_prefetch0((void *)(uintptr_t)desc_addr);
-
- virtio_enqueue_offload(m, (struct virtio_net_hdr *)(uintptr_t)desc_addr);
- vhost_log_write(dev, desc->addr, dev->vhost_hlen);
- PRINT_PACKET(dev, (uintptr_t)desc_addr, dev->vhost_hlen, 0);
-
- desc_offset = dev->vhost_hlen;
- desc_avail = desc->len - dev->vhost_hlen;
+ uint16_t vec_id = *vec_idx;
- mbuf_avail = rte_pktmbuf_data_len(m);
- mbuf_offset = 0;
- while (mbuf_avail != 0 || m->next != NULL) {
- /* done with current mbuf, fetch next */
- if (mbuf_avail == 0) {
- m = m->next;
-
- mbuf_offset = 0;
- mbuf_avail = rte_pktmbuf_data_len(m);
- }
+ while (desc_len) {
+ uint64_t desc_addr;
+ uint64_t desc_chunck_len = desc_len;
- /* done with current desc buf, fetch next */
- if (desc_avail == 0) {
- if ((desc->flags & VRING_DESC_F_NEXT) == 0) {
- /* Room in vring buffer is not enough */
- error = -1;
- goto out;
- }
- if (unlikely(desc->next >= size || ++nr_desc > size)) {
- error = -1;
- goto out;
- }
+ if (unlikely(vec_id >= BUF_VECTOR_MAX))
+ return -1;
- desc = &descs[desc->next];
- desc_addr = vhost_iova_to_vva(dev, vq, desc->addr,
- desc->len,
- VHOST_ACCESS_RW);
- if (unlikely(!desc_addr)) {
- error = -1;
- goto out;
- }
+ desc_addr = vhost_iova_to_vva(dev, vq,
+ desc_iova,
+ &desc_chunck_len,
+ perm);
+ if (unlikely(!desc_addr))
+ return -1;
- desc_offset = 0;
- desc_avail = desc->len;
- }
+ rte_prefetch0((void *)(uintptr_t)desc_addr);
- cpy_len = RTE_MIN(desc_avail, mbuf_avail);
- if (likely(cpy_len > MAX_BATCH_LEN || copy_nb >= vq->size)) {
- rte_memcpy((void *)((uintptr_t)(desc_addr +
- desc_offset)),
- rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
- cpy_len);
- vhost_log_write(dev, desc->addr + desc_offset, cpy_len);
- PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset),
- cpy_len, 0);
- } else {
- batch_copy[copy_nb].dst =
- (void *)((uintptr_t)(desc_addr + desc_offset));
- batch_copy[copy_nb].src =
- rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
- batch_copy[copy_nb].log_addr = desc->addr + desc_offset;
- batch_copy[copy_nb].len = cpy_len;
- copy_nb++;
- }
+ 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;
- mbuf_avail -= cpy_len;
- mbuf_offset += cpy_len;
- desc_avail -= cpy_len;
- desc_offset += cpy_len;
+ desc_len -= desc_chunck_len;
+ desc_iova += desc_chunck_len;
+ vec_id++;
}
+ *vec_idx = vec_id;
-out:
- vq->batch_copy_nb_elems = copy_nb;
-
- return error;
+ return 0;
}
-/**
- * This function adds buffers to the virtio devices RX virtqueue. Buffers can
- * be received from the physical port or from another virtio device. A packet
- * count is returned to indicate the number of packets that are successfully
- * added to the RX queue. This function works when the mbuf is scattered, but
- * it doesn't support the mergeable feature.
- */
-static __rte_always_inline uint32_t
-virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count)
+static __rte_always_inline int
+fill_vec_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint32_t avail_idx, uint16_t *vec_idx,
+ struct buf_vector *buf_vec, uint16_t *desc_chain_head,
+ uint32_t *desc_chain_len, uint8_t perm)
{
- struct vhost_virtqueue *vq;
- uint16_t avail_idx, free_entries, start_idx;
- uint16_t desc_indexes[MAX_PKT_BURST];
- struct vring_desc *descs;
- uint16_t used_idx;
- uint32_t i, sz;
-
- LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
- }
+ uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
+ uint16_t vec_id = *vec_idx;
+ uint32_t len = 0;
+ uint64_t dlen;
+ uint32_t nr_descs = vq->size;
+ uint32_t cnt = 0;
+ struct vring_desc *descs = vq->desc;
+ struct vring_desc *idesc = NULL;
- vq = dev->virtqueue[queue_id];
- if (unlikely(vq->enabled == 0))
- return 0;
+ if (unlikely(idx >= vq->size))
+ return -1;
- if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
- vhost_user_iotlb_rd_lock(vq);
+ *desc_chain_head = idx;
- if (unlikely(vq->access_ok == 0)) {
- if (unlikely(vring_translate(dev, vq) < 0)) {
- count = 0;
- goto out;
- }
- }
+ if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) {
+ dlen = vq->desc[idx].len;
+ nr_descs = dlen / sizeof(struct vring_desc);
+ if (unlikely(nr_descs > vq->size))
+ return -1;
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- start_idx = vq->last_used_idx;
- free_entries = avail_idx - start_idx;
- count = RTE_MIN(count, free_entries);
- count = RTE_MIN(count, (uint32_t)MAX_PKT_BURST);
- if (count == 0)
- goto out;
+ descs = (struct vring_desc *)(uintptr_t)
+ vhost_iova_to_vva(dev, vq, vq->desc[idx].addr,
+ &dlen,
+ VHOST_ACCESS_RO);
+ if (unlikely(!descs))
+ return -1;
- LOG_DEBUG(VHOST_DATA, "(%d) start_idx %d | end_idx %d\n",
- dev->vid, start_idx, start_idx + count);
+ if (unlikely(dlen < vq->desc[idx].len)) {
+ /*
+ * The indirect desc table is not contiguous
+ * in process VA space, we have to copy it.
+ */
+ idesc = vhost_alloc_copy_ind_table(dev, vq,
+ vq->desc[idx].addr, vq->desc[idx].len);
+ if (unlikely(!idesc))
+ return -1;
- vq->batch_copy_nb_elems = 0;
+ descs = idesc;
+ }
- /* Retrieve all of the desc indexes first to avoid caching issues. */
- rte_prefetch0(&vq->avail->ring[start_idx & (vq->size - 1)]);
- for (i = 0; i < count; i++) {
- used_idx = (start_idx + i) & (vq->size - 1);
- desc_indexes[i] = vq->avail->ring[used_idx];
- vq->used->ring[used_idx].id = desc_indexes[i];
- vq->used->ring[used_idx].len = pkts[i]->pkt_len +
- dev->vhost_hlen;
- vhost_log_used_vring(dev, vq,
- offsetof(struct vring_used, ring[used_idx]),
- sizeof(vq->used->ring[used_idx]));
+ idx = 0;
}
- rte_prefetch0(&vq->desc[desc_indexes[0]]);
- for (i = 0; i < count; i++) {
- uint16_t desc_idx = desc_indexes[i];
- int err;
+ while (1) {
+ if (unlikely(idx >= nr_descs || cnt++ >= nr_descs)) {
+ free_ind_table(idesc);
+ return -1;
+ }
- if (vq->desc[desc_idx].flags & VRING_DESC_F_INDIRECT) {
- descs = (struct vring_desc *)(uintptr_t)
- vhost_iova_to_vva(dev,
- vq, vq->desc[desc_idx].addr,
- vq->desc[desc_idx].len,
- VHOST_ACCESS_RO);
- if (unlikely(!descs)) {
- count = i;
- break;
- }
+ len += descs[idx].len;
- desc_idx = 0;
- sz = vq->desc[desc_idx].len / sizeof(*descs);
- } else {
- descs = vq->desc;
- sz = vq->size;
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[idx].addr, descs[idx].len,
+ perm))) {
+ free_ind_table(idesc);
+ return -1;
}
- err = copy_mbuf_to_desc(dev, vq, descs, pkts[i], desc_idx, sz);
- if (unlikely(err)) {
- count = i;
+ if ((descs[idx].flags & VRING_DESC_F_NEXT) == 0)
break;
- }
- if (i + 1 < count)
- rte_prefetch0(&vq->desc[desc_indexes[i+1]]);
+ idx = descs[idx].next;
}
- do_data_copy_enqueue(dev, vq);
-
- rte_smp_wmb();
-
- *(volatile uint16_t *)&vq->used->idx += count;
- vq->last_used_idx += count;
- vhost_log_used_vring(dev, vq,
- offsetof(struct vring_used, idx),
- sizeof(vq->used->idx));
+ *desc_chain_len = len;
+ *vec_idx = vec_id;
- vhost_vring_call(vq);
-out:
- if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
- vhost_user_iotlb_rd_unlock(vq);
+ if (unlikely(!!idesc))
+ free_ind_table(idesc);
- return count;
-}
-
-static __rte_always_inline int
-fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq,
- uint32_t avail_idx, uint32_t *vec_idx,
- struct buf_vector *buf_vec, uint16_t *desc_chain_head,
- uint16_t *desc_chain_len)
-{
- uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)];
- uint32_t vec_id = *vec_idx;
- uint32_t len = 0;
- struct vring_desc *descs = vq->desc;
-
- *desc_chain_head = idx;
-
- if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) {
- descs = (struct vring_desc *)(uintptr_t)
- vhost_iova_to_vva(dev, vq, vq->desc[idx].addr,
- vq->desc[idx].len,
- VHOST_ACCESS_RO);
- if (unlikely(!descs))
- return -1;
-
- idx = 0;
- }
-
- while (1) {
- if (unlikely(vec_id >= BUF_VECTOR_MAX || idx >= vq->size))
- return -1;
-
- len += descs[idx].len;
- buf_vec[vec_id].buf_addr = descs[idx].addr;
- buf_vec[vec_id].buf_len = descs[idx].len;
- buf_vec[vec_id].desc_idx = idx;
- vec_id++;
-
- if ((descs[idx].flags & VRING_DESC_F_NEXT) == 0)
- break;
-
- idx = descs[idx].next;
- }
-
- *desc_chain_len = len;
- *vec_idx = vec_id;
-
- return 0;
+ return 0;
}
/*
* Returns -1 on fail, 0 on success
*/
static inline int
-reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq,
+reserve_avail_buf_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint32_t size, struct buf_vector *buf_vec,
- uint16_t *num_buffers, uint16_t avail_head)
+ uint16_t *num_buffers, uint16_t avail_head,
+ uint16_t *nr_vec)
{
uint16_t cur_idx;
- uint32_t vec_idx = 0;
- uint16_t tries = 0;
+ uint16_t vec_idx = 0;
+ uint16_t max_tries, tries = 0;
uint16_t head_idx = 0;
- uint16_t len = 0;
+ uint32_t len = 0;
*num_buffers = 0;
cur_idx = vq->last_avail_idx;
+ if (rxvq_is_mergeable(dev))
+ max_tries = vq->size - 1;
+ else
+ max_tries = 1;
+
while (size > 0) {
if (unlikely(cur_idx == avail_head))
return -1;
+ /*
+ * 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(dev, vq, cur_idx, &vec_idx, buf_vec,
- &head_idx, &len) < 0))
+ if (unlikely(fill_vec_buf_split(dev, vq, cur_idx,
+ &vec_idx, buf_vec,
+ &head_idx, &len,
+ VHOST_ACCESS_RW) < 0))
return -1;
len = RTE_MIN(len, size);
- update_shadow_used_ring(vq, head_idx, len);
+ update_shadow_used_ring_split(vq, head_idx, len);
size -= len;
cur_idx++;
- tries++;
*num_buffers += 1;
+ }
+
+ *nr_vec = vec_idx;
+
+ return 0;
+}
+
+static __rte_always_inline int
+fill_vec_buf_packed_indirect(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct vring_packed_desc *desc, uint16_t *vec_idx,
+ struct buf_vector *buf_vec, uint32_t *len, uint8_t perm)
+{
+ uint16_t i;
+ uint32_t nr_descs;
+ uint16_t vec_id = *vec_idx;
+ uint64_t dlen;
+ struct vring_packed_desc *descs, *idescs = NULL;
+
+ dlen = desc->len;
+ descs = (struct vring_packed_desc *)(uintptr_t)
+ vhost_iova_to_vva(dev, vq, desc->addr, &dlen, VHOST_ACCESS_RO);
+ if (unlikely(!descs))
+ return -1;
+ if (unlikely(dlen < desc->len)) {
/*
- * if we tried all available ring items, and still
- * can't get enough buf, it means something abnormal
- * happened.
+ * The indirect desc table is not contiguous
+ * in process VA space, we have to copy it.
*/
- if (unlikely(tries >= vq->size))
+ idescs = vhost_alloc_copy_ind_table(dev,
+ vq, desc->addr, desc->len);
+ if (unlikely(!idescs))
+ return -1;
+
+ descs = idescs;
+ }
+
+ nr_descs = desc->len / sizeof(struct vring_packed_desc);
+ if (unlikely(nr_descs >= vq->size)) {
+ free_ind_table(idescs);
+ return -1;
+ }
+
+ for (i = 0; i < nr_descs; i++) {
+ if (unlikely(vec_id >= BUF_VECTOR_MAX)) {
+ free_ind_table(idescs);
+ return -1;
+ }
+
+ *len += descs[i].len;
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[i].addr, descs[i].len,
+ perm)))
+ return -1;
+ }
+ *vec_idx = vec_id;
+
+ if (unlikely(!!idescs))
+ free_ind_table(idescs);
+
+ return 0;
+}
+
+static __rte_always_inline int
+fill_vec_buf_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ uint16_t avail_idx, uint16_t *desc_count,
+ struct buf_vector *buf_vec, uint16_t *vec_idx,
+ uint16_t *buf_id, uint32_t *len, uint8_t perm)
+{
+ bool wrap_counter = vq->avail_wrap_counter;
+ struct vring_packed_desc *descs = vq->desc_packed;
+ uint16_t vec_id = *vec_idx;
+
+ if (avail_idx < vq->last_avail_idx)
+ wrap_counter ^= 1;
+
+ /*
+ * Perform a load-acquire barrier in desc_is_avail to
+ * enforce the ordering between desc flags and desc
+ * content.
+ */
+ if (unlikely(!desc_is_avail(&descs[avail_idx], wrap_counter)))
+ return -1;
+
+ *desc_count = 0;
+ *len = 0;
+
+ while (1) {
+ if (unlikely(vec_id >= BUF_VECTOR_MAX))
+ return -1;
+
+ if (unlikely(*desc_count >= vq->size))
return -1;
+
+ *desc_count += 1;
+ *buf_id = descs[avail_idx].id;
+
+ if (descs[avail_idx].flags & VRING_DESC_F_INDIRECT) {
+ if (unlikely(fill_vec_buf_packed_indirect(dev, vq,
+ &descs[avail_idx],
+ &vec_id, buf_vec,
+ len, perm) < 0))
+ return -1;
+ } else {
+ *len += descs[avail_idx].len;
+
+ if (unlikely(map_one_desc(dev, vq, buf_vec, &vec_id,
+ descs[avail_idx].addr,
+ descs[avail_idx].len,
+ perm)))
+ return -1;
+ }
+
+ if ((descs[avail_idx].flags & VRING_DESC_F_NEXT) == 0)
+ break;
+
+ if (++avail_idx >= vq->size) {
+ avail_idx -= vq->size;
+ wrap_counter ^= 1;
+ }
}
+ *vec_idx = vec_id;
+
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_iova(dev, vq,
+ iova, len);
+
+ remain -= len;
+ iova += len;
+ src += len;
+ buf_vec++;
+ }
+}
+
static __rte_always_inline int
-copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq,
+copy_mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
struct rte_mbuf *m, struct buf_vector *buf_vec,
- uint16_t num_buffers)
+ uint16_t nr_vec, uint16_t num_buffers)
{
uint32_t vec_idx = 0;
- uint64_t desc_addr;
uint32_t mbuf_offset, mbuf_avail;
- uint32_t desc_offset, desc_avail;
+ uint32_t buf_offset, buf_avail;
+ uint64_t buf_addr, buf_iova, buf_len;
uint32_t cpy_len;
- uint64_t hdr_addr, hdr_phys_addr;
+ uint64_t hdr_addr;
struct rte_mbuf *hdr_mbuf;
struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
- uint16_t copy_nb = vq->batch_copy_nb_elems;
+ struct virtio_net_hdr_mrg_rxbuf tmp_hdr, *hdr = NULL;
int error = 0;
if (unlikely(m == NULL)) {
goto out;
}
- desc_addr = vhost_iova_to_vva(dev, vq, buf_vec[vec_idx].buf_addr,
- buf_vec[vec_idx].buf_len,
- VHOST_ACCESS_RW);
- if (buf_vec[vec_idx].buf_len < dev->vhost_hlen || !desc_addr) {
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+
+ if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
error = -1;
goto out;
}
hdr_mbuf = m;
- hdr_addr = desc_addr;
- hdr_phys_addr = buf_vec[vec_idx].buf_addr;
- rte_prefetch0((void *)(uintptr_t)hdr_addr);
+ hdr_addr = buf_addr;
+ if (unlikely(buf_len < dev->vhost_hlen))
+ hdr = &tmp_hdr;
+ else
+ hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)hdr_addr;
- LOG_DEBUG(VHOST_DATA, "(%d) RX: num merge buffers %d\n",
+ VHOST_LOG_DATA(DEBUG, "(%d) RX: num merge buffers %d\n",
dev->vid, num_buffers);
- desc_avail = buf_vec[vec_idx].buf_len - dev->vhost_hlen;
- desc_offset = dev->vhost_hlen;
+ if (unlikely(buf_len < dev->vhost_hlen)) {
+ buf_offset = dev->vhost_hlen - buf_len;
+ vec_idx++;
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+ buf_avail = buf_len - buf_offset;
+ } else {
+ buf_offset = dev->vhost_hlen;
+ buf_avail = buf_len - dev->vhost_hlen;
+ }
mbuf_avail = rte_pktmbuf_data_len(m);
mbuf_offset = 0;
while (mbuf_avail != 0 || m->next != NULL) {
- /* done with current desc buf, get the next one */
- if (desc_avail == 0) {
+ /* done with current buf, get the next one */
+ if (buf_avail == 0) {
vec_idx++;
- desc_addr =
- vhost_iova_to_vva(dev, vq,
- buf_vec[vec_idx].buf_addr,
- buf_vec[vec_idx].buf_len,
- VHOST_ACCESS_RW);
- if (unlikely(!desc_addr)) {
+ if (unlikely(vec_idx >= nr_vec)) {
error = -1;
goto out;
}
- /* Prefetch buffer address. */
- rte_prefetch0((void *)(uintptr_t)desc_addr);
- desc_offset = 0;
- desc_avail = buf_vec[vec_idx].buf_len;
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+
+ buf_offset = 0;
+ buf_avail = buf_len;
}
/* done with current mbuf, get the next one */
}
if (hdr_addr) {
- struct virtio_net_hdr_mrg_rxbuf *hdr;
-
- hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)
- hdr_addr;
virtio_enqueue_offload(hdr_mbuf, &hdr->hdr);
- ASSIGN_UNLESS_EQUAL(hdr->num_buffers, num_buffers);
+ if (rxvq_is_mergeable(dev))
+ ASSIGN_UNLESS_EQUAL(hdr->num_buffers,
+ num_buffers);
- vhost_log_write(dev, hdr_phys_addr, dev->vhost_hlen);
- PRINT_PACKET(dev, (uintptr_t)hdr_addr,
- dev->vhost_hlen, 0);
+ if (unlikely(hdr == &tmp_hdr)) {
+ copy_vnet_hdr_to_desc(dev, vq, buf_vec, hdr);
+ } else {
+ PRINT_PACKET(dev, (uintptr_t)hdr_addr,
+ dev->vhost_hlen, 0);
+ vhost_log_cache_write_iova(dev, vq,
+ buf_vec[0].buf_iova,
+ dev->vhost_hlen);
+ }
hdr_addr = 0;
}
- cpy_len = RTE_MIN(desc_avail, mbuf_avail);
+ cpy_len = RTE_MIN(buf_avail, mbuf_avail);
- if (likely(cpy_len > MAX_BATCH_LEN || copy_nb >= vq->size)) {
- rte_memcpy((void *)((uintptr_t)(desc_addr +
- desc_offset)),
+ if (likely(cpy_len > MAX_BATCH_LEN ||
+ vq->batch_copy_nb_elems >= vq->size)) {
+ rte_memcpy((void *)((uintptr_t)(buf_addr + buf_offset)),
rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
cpy_len);
- vhost_log_write(dev,
- buf_vec[vec_idx].buf_addr + desc_offset,
- cpy_len);
- PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset),
+ vhost_log_cache_write_iova(dev, vq,
+ buf_iova + buf_offset,
+ cpy_len);
+ PRINT_PACKET(dev, (uintptr_t)(buf_addr + buf_offset),
cpy_len, 0);
} else {
- batch_copy[copy_nb].dst =
- (void *)((uintptr_t)(desc_addr + desc_offset));
- batch_copy[copy_nb].src =
+ batch_copy[vq->batch_copy_nb_elems].dst =
+ (void *)((uintptr_t)(buf_addr + buf_offset));
+ batch_copy[vq->batch_copy_nb_elems].src =
rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
- batch_copy[copy_nb].log_addr =
- buf_vec[vec_idx].buf_addr + desc_offset;
- batch_copy[copy_nb].len = cpy_len;
- copy_nb++;
+ batch_copy[vq->batch_copy_nb_elems].log_addr =
+ buf_iova + buf_offset;
+ batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
+ vq->batch_copy_nb_elems++;
}
mbuf_avail -= cpy_len;
mbuf_offset += cpy_len;
- desc_avail -= cpy_len;
- desc_offset += cpy_len;
+ buf_avail -= cpy_len;
+ buf_offset += cpy_len;
}
out:
- vq->batch_copy_nb_elems = copy_nb;
return error;
}
-static __rte_always_inline uint32_t
-virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id,
- struct rte_mbuf **pkts, uint32_t count)
+static __rte_always_inline int
+vhost_enqueue_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf *pkt,
+ struct buf_vector *buf_vec,
+ uint16_t *nr_descs)
{
- struct vhost_virtqueue *vq;
- uint32_t pkt_idx = 0;
- uint16_t num_buffers;
- struct buf_vector buf_vec[BUF_VECTOR_MAX];
- uint16_t avail_head;
+ 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;
+ uint32_t size = pkt->pkt_len + dev->vhost_hlen;
+ uint16_t num_buffers = 0;
+ 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;
- LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 0, dev->nr_vring))) {
- RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
+ 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[num_buffers] = len;
+ buffer_buf_id[num_buffers] = buf_id;
+ buffer_desc_count[num_buffers] = desc_count;
+ num_buffers += 1;
+
+ *nr_descs += desc_count;
+ avail_idx += desc_count;
+ if (avail_idx >= vq->size)
+ avail_idx -= vq->size;
}
- vq = dev->virtqueue[queue_id];
- if (unlikely(vq->enabled == 0))
- return 0;
+ if (copy_mbuf_to_desc(dev, vq, pkt, buf_vec, nr_vec, num_buffers) < 0)
+ return -1;
- if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
- vhost_user_iotlb_rd_lock(vq);
+ vhost_shadow_enqueue_single_packed(dev, vq, buffer_len, buffer_buf_id,
+ buffer_desc_count, num_buffers);
- if (unlikely(vq->access_ok == 0))
- if (unlikely(vring_translate(dev, vq) < 0))
- goto out;
+ return 0;
+}
- count = RTE_MIN((uint32_t)MAX_PKT_BURST, count);
- if (count == 0)
- goto out;
+static __rte_noinline uint32_t
+virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts, uint32_t count)
+{
+ uint32_t pkt_idx = 0;
+ uint16_t num_buffers;
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ uint16_t avail_head;
- vq->batch_copy_nb_elems = 0;
+ /*
+ * The ordering between avail index and
+ * desc reads needs to be enforced.
+ */
+ avail_head = __atomic_load_n(&vq->avail->idx, __ATOMIC_ACQUIRE);
rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
- vq->shadow_used_idx = 0;
- avail_head = *((volatile uint16_t *)&vq->avail->idx);
for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen;
+ uint16_t nr_vec = 0;
- if (unlikely(reserve_avail_buf_mergeable(dev, vq,
+ if (unlikely(reserve_avail_buf_split(dev, vq,
pkt_len, buf_vec, &num_buffers,
- avail_head) < 0)) {
- LOG_DEBUG(VHOST_DATA,
+ avail_head, &nr_vec) < 0)) {
+ VHOST_LOG_DATA(DEBUG,
"(%d) failed to get enough desc from vring\n",
dev->vid);
vq->shadow_used_idx -= num_buffers;
break;
}
- LOG_DEBUG(VHOST_DATA, "(%d) current index %d | end index %d\n",
+ VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
dev->vid, vq->last_avail_idx,
vq->last_avail_idx + num_buffers);
- if (copy_mbuf_to_desc_mergeable(dev, vq, pkts[pkt_idx],
- buf_vec, num_buffers) < 0) {
+ if (copy_mbuf_to_desc(dev, vq, pkts[pkt_idx],
+ buf_vec, nr_vec,
+ num_buffers) < 0) {
vq->shadow_used_idx -= num_buffers;
break;
}
do_data_copy_enqueue(dev, vq);
if (likely(vq->shadow_used_idx)) {
- flush_shadow_used_ring(dev, vq);
- vhost_vring_call(vq);
+ flush_shadow_used_ring_split(dev, vq);
+ vhost_vring_call_split(dev, vq);
}
-out:
- if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
- vhost_user_iotlb_rd_unlock(vq);
-
return pkt_idx;
}
-uint16_t
-rte_vhost_enqueue_burst(int vid, uint16_t queue_id,
- struct rte_mbuf **pkts, uint16_t count)
+static __rte_always_inline int
+virtio_dev_rx_batch_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts)
{
- struct virtio_net *dev = get_device(vid);
+ 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 = dev->vhost_hlen;
+ uint64_t lens[PACKED_BATCH_SIZE];
+ uint16_t ids[PACKED_BATCH_SIZE];
+ uint16_t i;
- if (!dev)
- return 0;
+ if (unlikely(avail_idx & PACKED_BATCH_MASK))
+ return -1;
- if (dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF))
- return virtio_dev_merge_rx(dev, queue_id, pkts, count);
- else
- return virtio_dev_rx(dev, queue_id, pkts, count);
-}
+ if (unlikely((avail_idx + PACKED_BATCH_SIZE) > vq->size))
+ return -1;
-static inline bool
-virtio_net_with_host_offload(struct virtio_net *dev)
-{
- if (dev->features &
- ((1ULL << VIRTIO_NET_F_CSUM) |
- (1ULL << VIRTIO_NET_F_HOST_ECN) |
- (1ULL << VIRTIO_NET_F_HOST_TSO4) |
- (1ULL << VIRTIO_NET_F_HOST_TSO6) |
- (1ULL << VIRTIO_NET_F_HOST_UFO)))
- return true;
+ 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;
+ }
- return false;
-}
+ rte_smp_rmb();
-static void
-parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr)
-{
- struct ipv4_hdr *ipv4_hdr;
- struct ipv6_hdr *ipv6_hdr;
- void *l3_hdr = NULL;
- struct ether_hdr *eth_hdr;
- uint16_t ethertype;
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ lens[i] = descs[avail_idx + i].len;
- eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(pkts[i]->pkt_len > (lens[i] - buf_offset)))
+ return -1;
+ }
- m->l2_len = sizeof(struct ether_hdr);
- ethertype = rte_be_to_cpu_16(eth_hdr->ether_type);
+ 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);
- if (ethertype == ETHER_TYPE_VLAN) {
- struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1);
+ 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;
+ }
- m->l2_len += sizeof(struct vlan_hdr);
- ethertype = rte_be_to_cpu_16(vlan_hdr->eth_proto);
+ 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 *)
+ (uintptr_t)desc_addrs[i];
+ lens[i] = pkts[i]->pkt_len + dev->vhost_hlen;
}
- l3_hdr = (char *)eth_hdr + m->l2_len;
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ virtio_enqueue_offload(pkts[i], &hdrs[i]->hdr);
- switch (ethertype) {
- case ETHER_TYPE_IPv4:
- ipv4_hdr = l3_hdr;
- *l4_proto = ipv4_hdr->next_proto_id;
- m->l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4;
- *l4_hdr = (char *)l3_hdr + m->l3_len;
- m->ol_flags |= PKT_TX_IPV4;
- break;
- case ETHER_TYPE_IPv6:
- ipv6_hdr = l3_hdr;
- *l4_proto = ipv6_hdr->proto;
- m->l3_len = sizeof(struct ipv6_hdr);
- *l4_hdr = (char *)l3_hdr + m->l3_len;
- m->ol_flags |= PKT_TX_IPV6;
- break;
- default:
- m->l3_len = 0;
- *l4_proto = 0;
- *l4_hdr = NULL;
- break;
+ vq_inc_last_avail_packed(vq, PACKED_BATCH_SIZE);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ rte_memcpy((void *)(uintptr_t)(desc_addrs[i] + buf_offset),
+ rte_pktmbuf_mtod_offset(pkts[i], void *, 0),
+ pkts[i]->pkt_len);
}
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ vhost_log_cache_write_iova(dev, vq, descs[avail_idx + i].addr,
+ lens[i]);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ ids[i] = descs[avail_idx + i].id;
+
+ vhost_flush_enqueue_batch_packed(dev, vq, lens, ids);
+
+ return 0;
}
-static __rte_always_inline void
-vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
+static __rte_always_inline int16_t
+virtio_dev_rx_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf *pkt)
{
- uint16_t l4_proto = 0;
- void *l4_hdr = NULL;
- struct tcp_hdr *tcp_hdr = NULL;
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ uint16_t nr_descs = 0;
- if (hdr->flags == 0 && hdr->gso_type == VIRTIO_NET_HDR_GSO_NONE)
- return;
+ rte_smp_rmb();
+ if (unlikely(vhost_enqueue_single_packed(dev, vq, pkt, buf_vec,
+ &nr_descs) < 0)) {
+ VHOST_LOG_DATA(DEBUG,
+ "(%d) failed to get enough desc from vring\n",
+ dev->vid);
+ return -1;
+ }
- 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 tcp_hdr, cksum)):
- if (l4_proto == IPPROTO_TCP)
- m->ol_flags |= PKT_TX_TCP_CKSUM;
- break;
- case (offsetof(struct udp_hdr, dgram_cksum)):
- if (l4_proto == IPPROTO_UDP)
- m->ol_flags |= PKT_TX_UDP_CKSUM;
- break;
- case (offsetof(struct sctp_hdr, cksum)):
- if (l4_proto == IPPROTO_SCTP)
- m->ol_flags |= PKT_TX_SCTP_CKSUM;
- break;
+ VHOST_LOG_DATA(DEBUG, "(%d) current index %d | end index %d\n",
+ dev->vid, vq->last_avail_idx,
+ vq->last_avail_idx + nr_descs);
+
+ vq_inc_last_avail_packed(vq, nr_descs);
+
+ return 0;
+}
+
+static __rte_noinline uint32_t
+virtio_dev_rx_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mbuf **pkts,
+ 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,
+ &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);
+
+ if (vq->shadow_used_idx) {
+ do_data_copy_enqueue(dev, vq);
+ vhost_flush_enqueue_shadow_packed(dev, vq);
+ }
+
+ if (pkt_idx)
+ vhost_vring_call_packed(dev, vq);
+
+ return pkt_idx;
+}
+
+static __rte_always_inline uint32_t
+virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint32_t 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;
+ }
+
+ vq = dev->virtqueue[queue_id];
+
+ rte_spinlock_lock(&vq->access_lock);
+
+ if (unlikely(vq->enabled == 0))
+ goto out_access_unlock;
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
+ if (unlikely(vq->access_ok == 0))
+ if (unlikely(vring_translate(dev, vq) < 0))
+ goto out;
+
+ count = RTE_MIN((uint32_t)MAX_PKT_BURST, count);
+ if (count == 0)
+ goto out;
+
+ if (vq_is_packed(dev))
+ nb_tx = virtio_dev_rx_packed(dev, vq, pkts, count);
+ else
+ nb_tx = virtio_dev_rx_split(dev, vq, pkts, count);
+
+out:
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_unlock(vq);
+
+out_access_unlock:
+ rte_spinlock_unlock(&vq->access_lock);
+
+ return nb_tx;
+}
+
+uint16_t
+rte_vhost_enqueue_burst(int vid, uint16_t queue_id,
+ struct rte_mbuf **pkts, uint16_t count)
+{
+ struct virtio_net *dev = get_device(vid);
+
+ if (!dev)
+ return 0;
+
+ if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+ VHOST_LOG_DATA(ERR,
+ "(%d) %s: built-in vhost net backend is disabled.\n",
+ dev->vid, __func__);
+ return 0;
+ }
+
+ return virtio_dev_rx(dev, queue_id, pkts, count);
+}
+
+static inline bool
+virtio_net_with_host_offload(struct virtio_net *dev)
+{
+ if (dev->features &
+ ((1ULL << VIRTIO_NET_F_CSUM) |
+ (1ULL << VIRTIO_NET_F_HOST_ECN) |
+ (1ULL << VIRTIO_NET_F_HOST_TSO4) |
+ (1ULL << VIRTIO_NET_F_HOST_TSO6) |
+ (1ULL << VIRTIO_NET_F_HOST_UFO)))
+ return true;
+
+ return false;
+}
+
+static void
+parse_ethernet(struct rte_mbuf *m, uint16_t *l4_proto, void **l4_hdr)
+{
+ 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;
+
+ eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+
+ m->l2_len = sizeof(struct rte_ether_hdr);
+ ethertype = rte_be_to_cpu_16(eth_hdr->ether_type);
+
+ if (ethertype == RTE_ETHER_TYPE_VLAN) {
+ struct rte_vlan_hdr *vlan_hdr =
+ (struct rte_vlan_hdr *)(eth_hdr + 1);
+
+ m->l2_len += sizeof(struct rte_vlan_hdr);
+ 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;
+ m->l3_len = (ipv4_hdr->version_ihl & 0x0f) * 4;
+ *l4_hdr = (char *)l3_hdr + m->l3_len;
+ m->ol_flags |= PKT_TX_IPV4;
+ break;
+ case RTE_ETHER_TYPE_IPV6:
+ ipv6_hdr = l3_hdr;
+ *l4_proto = ipv6_hdr->proto;
+ m->l3_len = sizeof(struct rte_ipv6_hdr);
+ *l4_hdr = (char *)l3_hdr + m->l3_len;
+ m->ol_flags |= PKT_TX_IPV6;
+ break;
+ default:
+ m->l3_len = 0;
+ *l4_proto = 0;
+ *l4_hdr = NULL;
+ break;
+ }
+}
+
+static __rte_always_inline void
+vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m)
+{
+ uint16_t l4_proto = 0;
+ void *l4_hdr = NULL;
+ struct rte_tcp_hdr *tcp_hdr = NULL;
+
+ if (hdr->flags == 0 && hdr->gso_type == VIRTIO_NET_HDR_GSO_NONE)
+ 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;
+ break;
+ case (offsetof(struct rte_udp_hdr, dgram_cksum)):
+ if (l4_proto == IPPROTO_UDP)
+ 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;
+ break;
default:
break;
}
m->tso_segsz = hdr->gso_size;
m->l4_len = (tcp_hdr->data_off & 0xf0) >> 2;
break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ m->ol_flags |= PKT_TX_UDP_SEG;
+ m->tso_segsz = hdr->gso_size;
+ m->l4_len = sizeof(struct rte_udp_hdr);
+ break;
default:
- RTE_LOG(WARNING, VHOST_DATA,
+ VHOST_LOG_DATA(WARNING,
"unsupported gso type %u.\n", hdr->gso_type);
break;
}
}
}
-#define RARP_PKT_SIZE 64
-
-static int
-make_rarp_packet(struct rte_mbuf *rarp_mbuf, const struct ether_addr *mac)
+static __rte_noinline void
+copy_vnet_hdr_from_desc(struct virtio_net_hdr *hdr,
+ struct buf_vector *buf_vec)
{
- struct ether_hdr *eth_hdr;
- struct arp_hdr *rarp;
-
- if (rarp_mbuf->buf_len < 64) {
- RTE_LOG(WARNING, VHOST_DATA,
- "failed to make RARP; mbuf size too small %u (< %d)\n",
- rarp_mbuf->buf_len, RARP_PKT_SIZE);
- return -1;
+ 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++;
}
-
- /* Ethernet header. */
- eth_hdr = rte_pktmbuf_mtod_offset(rarp_mbuf, struct ether_hdr *, 0);
- memset(eth_hdr->d_addr.addr_bytes, 0xff, ETHER_ADDR_LEN);
- ether_addr_copy(mac, ð_hdr->s_addr);
- eth_hdr->ether_type = htons(ETHER_TYPE_RARP);
-
- /* RARP header. */
- rarp = (struct arp_hdr *)(eth_hdr + 1);
- rarp->arp_hrd = htons(ARP_HRD_ETHER);
- rarp->arp_pro = htons(ETHER_TYPE_IPv4);
- rarp->arp_hln = ETHER_ADDR_LEN;
- rarp->arp_pln = 4;
- rarp->arp_op = htons(ARP_OP_REVREQUEST);
-
- ether_addr_copy(mac, &rarp->arp_data.arp_sha);
- ether_addr_copy(mac, &rarp->arp_data.arp_tha);
- memset(&rarp->arp_data.arp_sip, 0x00, 4);
- memset(&rarp->arp_data.arp_tip, 0x00, 4);
-
- rarp_mbuf->pkt_len = rarp_mbuf->data_len = RARP_PKT_SIZE;
-
- return 0;
-}
-
-static __rte_always_inline void
-put_zmbuf(struct zcopy_mbuf *zmbuf)
-{
- zmbuf->in_use = 0;
}
static __rte_always_inline int
copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
- struct vring_desc *descs, uint16_t max_desc,
- struct rte_mbuf *m, uint16_t desc_idx,
- struct rte_mempool *mbuf_pool)
+ struct buf_vector *buf_vec, uint16_t nr_vec,
+ struct rte_mbuf *m, struct rte_mempool *mbuf_pool)
{
- struct vring_desc *desc;
- uint64_t desc_addr;
- uint32_t desc_avail, desc_offset;
+ uint32_t buf_avail, buf_offset;
+ uint64_t buf_addr, buf_iova, buf_len;
uint32_t mbuf_avail, mbuf_offset;
uint32_t cpy_len;
struct rte_mbuf *cur = m, *prev = m;
+ struct virtio_net_hdr tmp_hdr;
struct virtio_net_hdr *hdr = NULL;
/* A counter to avoid desc dead loop chain */
- uint32_t nr_desc = 1;
+ uint16_t vec_idx = 0;
struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
- uint16_t copy_nb = vq->batch_copy_nb_elems;
int error = 0;
- desc = &descs[desc_idx];
- if (unlikely((desc->len < dev->vhost_hlen)) ||
- (desc->flags & VRING_DESC_F_INDIRECT)) {
- error = -1;
- goto out;
- }
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
- desc_addr = vhost_iova_to_vva(dev,
- vq, desc->addr,
- desc->len,
- VHOST_ACCESS_RO);
- if (unlikely(!desc_addr)) {
+ if (unlikely(buf_len < dev->vhost_hlen && nr_vec <= 1)) {
error = -1;
goto out;
}
if (virtio_net_with_host_offload(dev)) {
- hdr = (struct virtio_net_hdr *)((uintptr_t)desc_addr);
- rte_prefetch0(hdr);
+ if (unlikely(buf_len < sizeof(struct virtio_net_hdr))) {
+ /*
+ * No luck, the virtio-net header doesn't fit
+ * in a contiguous virtual area.
+ */
+ copy_vnet_hdr_from_desc(&tmp_hdr, buf_vec);
+ hdr = &tmp_hdr;
+ } else {
+ hdr = (struct virtio_net_hdr *)((uintptr_t)buf_addr);
+ }
}
/*
* for Tx: the first for storing the header, and others
* for storing the data.
*/
- if (likely((desc->len == dev->vhost_hlen) &&
- (desc->flags & VRING_DESC_F_NEXT) != 0)) {
- desc = &descs[desc->next];
- if (unlikely(desc->flags & VRING_DESC_F_INDIRECT)) {
- error = -1;
- goto out;
- }
-
- desc_addr = vhost_iova_to_vva(dev,
- vq, desc->addr,
- desc->len,
- VHOST_ACCESS_RO);
- if (unlikely(!desc_addr)) {
- error = -1;
+ if (unlikely(buf_len < dev->vhost_hlen)) {
+ buf_offset = dev->vhost_hlen - buf_len;
+ vec_idx++;
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
+ buf_avail = buf_len - buf_offset;
+ } else if (buf_len == dev->vhost_hlen) {
+ if (unlikely(++vec_idx >= nr_vec))
goto out;
- }
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
- desc_offset = 0;
- desc_avail = desc->len;
- nr_desc += 1;
+ buf_offset = 0;
+ buf_avail = buf_len;
} else {
- desc_avail = desc->len - dev->vhost_hlen;
- desc_offset = dev->vhost_hlen;
+ buf_offset = dev->vhost_hlen;
+ buf_avail = buf_vec[vec_idx].buf_len - dev->vhost_hlen;
}
- rte_prefetch0((void *)(uintptr_t)(desc_addr + desc_offset));
-
- PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset), desc_avail, 0);
+ PRINT_PACKET(dev,
+ (uintptr_t)(buf_addr + buf_offset),
+ (uint32_t)buf_avail, 0);
mbuf_offset = 0;
mbuf_avail = m->buf_len - RTE_PKTMBUF_HEADROOM;
while (1) {
uint64_t hpa;
- cpy_len = RTE_MIN(desc_avail, mbuf_avail);
+ cpy_len = RTE_MIN(buf_avail, mbuf_avail);
/*
* A desc buf might across two host physical pages that are
* will be copied even though zero copy is enabled.
*/
if (unlikely(dev->dequeue_zero_copy && (hpa = gpa_to_hpa(dev,
- desc->addr + desc_offset, cpy_len)))) {
+ buf_iova + buf_offset, cpy_len)))) {
cur->data_len = cpy_len;
cur->data_off = 0;
- cur->buf_addr = (void *)(uintptr_t)(desc_addr
- + desc_offset);
+ cur->buf_addr =
+ (void *)(uintptr_t)(buf_addr + buf_offset);
cur->buf_iova = hpa;
/*
mbuf_avail = cpy_len;
} else {
if (likely(cpy_len > MAX_BATCH_LEN ||
- copy_nb >= vq->size ||
+ vq->batch_copy_nb_elems >= vq->size ||
(hdr && cur == m))) {
rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *,
mbuf_offset),
- (void *)((uintptr_t)(desc_addr +
- desc_offset)),
+ (void *)((uintptr_t)(buf_addr +
+ buf_offset)),
cpy_len);
} else {
- batch_copy[copy_nb].dst =
+ batch_copy[vq->batch_copy_nb_elems].dst =
rte_pktmbuf_mtod_offset(cur, void *,
mbuf_offset);
- batch_copy[copy_nb].src =
- (void *)((uintptr_t)(desc_addr +
- desc_offset));
- batch_copy[copy_nb].len = cpy_len;
- copy_nb++;
+ batch_copy[vq->batch_copy_nb_elems].src =
+ (void *)((uintptr_t)(buf_addr +
+ buf_offset));
+ batch_copy[vq->batch_copy_nb_elems].len =
+ cpy_len;
+ vq->batch_copy_nb_elems++;
}
}
mbuf_avail -= cpy_len;
mbuf_offset += cpy_len;
- desc_avail -= cpy_len;
- desc_offset += cpy_len;
+ buf_avail -= cpy_len;
+ buf_offset += cpy_len;
- /* This desc reaches to its end, get the next one */
- if (desc_avail == 0) {
- if ((desc->flags & VRING_DESC_F_NEXT) == 0)
+ /* This buf reaches to its end, get the next one */
+ if (buf_avail == 0) {
+ if (++vec_idx >= nr_vec)
break;
- if (unlikely(desc->next >= max_desc ||
- ++nr_desc > max_desc)) {
- error = -1;
- goto out;
- }
- desc = &descs[desc->next];
- if (unlikely(desc->flags & VRING_DESC_F_INDIRECT)) {
- error = -1;
- goto out;
- }
+ buf_addr = buf_vec[vec_idx].buf_addr;
+ buf_iova = buf_vec[vec_idx].buf_iova;
+ buf_len = buf_vec[vec_idx].buf_len;
- desc_addr = vhost_iova_to_vva(dev,
- vq, desc->addr,
- desc->len,
- VHOST_ACCESS_RO);
- if (unlikely(!desc_addr)) {
- error = -1;
- goto out;
- }
-
- rte_prefetch0((void *)(uintptr_t)desc_addr);
+ buf_offset = 0;
+ buf_avail = buf_len;
- desc_offset = 0;
- desc_avail = desc->len;
-
- PRINT_PACKET(dev, (uintptr_t)desc_addr, desc->len, 0);
+ PRINT_PACKET(dev, (uintptr_t)buf_addr,
+ (uint32_t)buf_avail, 0);
}
/*
if (mbuf_avail == 0) {
cur = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(cur == NULL)) {
- RTE_LOG(ERR, VHOST_DATA, "Failed to "
+ VHOST_LOG_DATA(ERR, "Failed to "
"allocate memory for mbuf.\n");
error = -1;
goto out;
vhost_dequeue_offload(hdr, m);
out:
- vq->batch_copy_nb_elems = copy_nb;
return error;
}
-static __rte_always_inline void
-update_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq,
- uint32_t used_idx, uint32_t desc_idx)
-{
- vq->used->ring[used_idx].id = desc_idx;
- vq->used->ring[used_idx].len = 0;
- vhost_log_used_vring(dev, vq,
- offsetof(struct vring_used, ring[used_idx]),
- sizeof(vq->used->ring[used_idx]));
-}
-
-static __rte_always_inline void
-update_used_idx(struct virtio_net *dev, struct vhost_virtqueue *vq,
- uint32_t count)
-{
- if (unlikely(count == 0))
- return;
-
- rte_smp_wmb();
- rte_smp_rmb();
-
- vq->used->idx += count;
- vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx),
- sizeof(vq->used->idx));
- vhost_vring_call(vq);
-}
-
static __rte_always_inline struct zcopy_mbuf *
get_zmbuf(struct vhost_virtqueue *vq)
{
return NULL;
}
-static __rte_always_inline bool
-mbuf_is_consumed(struct rte_mbuf *m)
+static void
+virtio_dev_extbuf_free(void *addr __rte_unused, void *opaque)
+{
+ rte_free(opaque);
+}
+
+static int
+virtio_dev_extbuf_alloc(struct rte_mbuf *pkt, uint32_t size)
{
- while (m) {
- if (rte_mbuf_refcnt_read(m) > 1)
- return false;
- m = m->next;
+ struct rte_mbuf_ext_shared_info *shinfo = NULL;
+ uint32_t total_len = RTE_PKTMBUF_HEADROOM + size;
+ uint16_t buf_len;
+ rte_iova_t iova;
+ void *buf;
+
+ /* Try to use pkt buffer to store shinfo to reduce the amount of memory
+ * required, otherwise store shinfo in the new buffer.
+ */
+ if (rte_pktmbuf_tailroom(pkt) >= sizeof(*shinfo))
+ shinfo = rte_pktmbuf_mtod(pkt,
+ struct rte_mbuf_ext_shared_info *);
+ else {
+ total_len += sizeof(*shinfo) + sizeof(uintptr_t);
+ total_len = RTE_ALIGN_CEIL(total_len, sizeof(uintptr_t));
}
- return true;
+ if (unlikely(total_len > UINT16_MAX))
+ return -ENOSPC;
+
+ buf_len = total_len;
+ buf = rte_malloc(NULL, buf_len, RTE_CACHE_LINE_SIZE);
+ if (unlikely(buf == NULL))
+ return -ENOMEM;
+
+ /* Initialize shinfo */
+ if (shinfo) {
+ shinfo->free_cb = virtio_dev_extbuf_free;
+ shinfo->fcb_opaque = buf;
+ rte_mbuf_ext_refcnt_set(shinfo, 1);
+ } else {
+ shinfo = rte_pktmbuf_ext_shinfo_init_helper(buf, &buf_len,
+ virtio_dev_extbuf_free, buf);
+ if (unlikely(shinfo == NULL)) {
+ rte_free(buf);
+ VHOST_LOG_DATA(ERR, "Failed to init shinfo\n");
+ return -1;
+ }
+ }
+
+ iova = rte_malloc_virt2iova(buf);
+ rte_pktmbuf_attach_extbuf(pkt, buf, iova, buf_len, shinfo);
+ rte_pktmbuf_reset_headroom(pkt);
+
+ return 0;
}
-uint16_t
-rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
- struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
+/*
+ * Allocate a host supported pktmbuf.
+ */
+static __rte_always_inline struct rte_mbuf *
+virtio_dev_pktmbuf_alloc(struct virtio_net *dev, struct rte_mempool *mp,
+ uint32_t data_len)
{
- struct virtio_net *dev;
- struct rte_mbuf *rarp_mbuf = NULL;
- struct vhost_virtqueue *vq;
- uint32_t desc_indexes[MAX_PKT_BURST];
- uint32_t used_idx;
- uint32_t i = 0;
- uint16_t free_entries;
- uint16_t avail_idx;
-
- dev = get_device(vid);
- if (!dev)
- return 0;
+ struct rte_mbuf *pkt = rte_pktmbuf_alloc(mp);
- if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, dev->nr_vring))) {
- RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n",
- dev->vid, __func__, queue_id);
- return 0;
+ if (unlikely(pkt == NULL)) {
+ VHOST_LOG_DATA(ERR,
+ "Failed to allocate memory for mbuf.\n");
+ return NULL;
}
- vq = dev->virtqueue[queue_id];
- if (unlikely(vq->enabled == 0))
- return 0;
+ if (rte_pktmbuf_tailroom(pkt) >= data_len)
+ return pkt;
- vq->batch_copy_nb_elems = 0;
+ /* attach an external buffer if supported */
+ if (dev->extbuf && !virtio_dev_extbuf_alloc(pkt, data_len))
+ return pkt;
- if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
- vhost_user_iotlb_rd_lock(vq);
+ /* check if chained buffers are allowed */
+ if (!dev->linearbuf)
+ return pkt;
- if (unlikely(vq->access_ok == 0))
- if (unlikely(vring_translate(dev, vq) < 0))
- goto out;
+ /* Data doesn't fit into the buffer and the host supports
+ * only linear buffers
+ */
+ rte_pktmbuf_free(pkt);
+
+ return NULL;
+}
+
+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)
+{
+ uint16_t i;
+ uint16_t free_entries;
if (unlikely(dev->dequeue_zero_copy)) {
struct zcopy_mbuf *zmbuf, *next;
- int nr_updated = 0;
for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
zmbuf != NULL; zmbuf = next) {
next = TAILQ_NEXT(zmbuf, next);
if (mbuf_is_consumed(zmbuf->mbuf)) {
- used_idx = vq->last_used_idx++ & (vq->size - 1);
- update_used_ring(dev, vq, used_idx,
- zmbuf->desc_idx);
- nr_updated += 1;
-
+ update_shadow_used_ring_split(vq,
+ zmbuf->desc_idx, 0);
TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
+ restore_mbuf(zmbuf->mbuf);
rte_pktmbuf_free(zmbuf->mbuf);
put_zmbuf(zmbuf);
vq->nr_zmbuf -= 1;
}
}
- update_used_idx(dev, vq, nr_updated);
+ if (likely(vq->shadow_used_idx)) {
+ flush_shadow_used_ring_split(dev, vq);
+ vhost_vring_call_split(dev, vq);
+ }
}
/*
- * Construct a RARP broadcast packet, and inject it to the "pkts"
- * array, to looks like that guest actually send such packet.
- *
- * Check user_send_rarp() for more information.
- *
- * 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.
- *
- * Prevent unnecessary false sharing by reading broadcast_rarp first
- * and only performing cmpset if the read indicates it is likely to
- * be set.
+ * The ordering between avail index and
+ * desc reads needs to be enforced.
*/
-
- if (unlikely(rte_atomic16_read(&dev->broadcast_rarp) &&
- rte_atomic16_cmpset((volatile uint16_t *)
- &dev->broadcast_rarp.cnt, 1, 0))) {
-
- rarp_mbuf = rte_pktmbuf_alloc(mbuf_pool);
- if (rarp_mbuf == NULL) {
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
- return 0;
- }
-
- if (make_rarp_packet(rarp_mbuf, &dev->mac)) {
- rte_pktmbuf_free(rarp_mbuf);
- rarp_mbuf = NULL;
- } else {
- count -= 1;
- }
- }
-
- free_entries = *((volatile uint16_t *)&vq->avail->idx) -
+ free_entries = __atomic_load_n(&vq->avail->idx, __ATOMIC_ACQUIRE) -
vq->last_avail_idx;
if (free_entries == 0)
- goto out;
+ return 0;
- LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__);
+ rte_prefetch0(&vq->avail->ring[vq->last_avail_idx & (vq->size - 1)]);
- /* Prefetch available and used ring */
- avail_idx = vq->last_avail_idx & (vq->size - 1);
- used_idx = vq->last_used_idx & (vq->size - 1);
- rte_prefetch0(&vq->avail->ring[avail_idx]);
- rte_prefetch0(&vq->used->ring[used_idx]);
+ VHOST_LOG_DATA(DEBUG, "(%d) %s\n", dev->vid, __func__);
count = RTE_MIN(count, MAX_PKT_BURST);
count = RTE_MIN(count, free_entries);
- LOG_DEBUG(VHOST_DATA, "(%d) about to dequeue %u buffers\n",
+ VHOST_LOG_DATA(DEBUG, "(%d) about to dequeue %u buffers\n",
dev->vid, count);
- /* Retrieve all of the head indexes first to avoid caching issues. */
for (i = 0; i < count; i++) {
- avail_idx = (vq->last_avail_idx + i) & (vq->size - 1);
- used_idx = (vq->last_used_idx + i) & (vq->size - 1);
- desc_indexes[i] = vq->avail->ring[avail_idx];
-
- if (likely(dev->dequeue_zero_copy == 0))
- update_used_ring(dev, vq, used_idx, desc_indexes[i]);
- }
-
- /* Prefetch descriptor index. */
- rte_prefetch0(&vq->desc[desc_indexes[0]]);
- for (i = 0; i < count; i++) {
- struct vring_desc *desc;
- uint16_t sz, idx;
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ uint16_t head_idx;
+ uint32_t buf_len;
+ uint16_t nr_vec = 0;
int err;
- if (likely(i + 1 < count))
- rte_prefetch0(&vq->desc[desc_indexes[i + 1]]);
-
- if (vq->desc[desc_indexes[i]].flags & VRING_DESC_F_INDIRECT) {
- desc = (struct vring_desc *)(uintptr_t)
- vhost_iova_to_vva(dev, vq,
- vq->desc[desc_indexes[i]].addr,
- sizeof(*desc),
- VHOST_ACCESS_RO);
- if (unlikely(!desc))
- break;
+ if (unlikely(fill_vec_buf_split(dev, vq,
+ vq->last_avail_idx + i,
+ &nr_vec, buf_vec,
+ &head_idx, &buf_len,
+ VHOST_ACCESS_RO) < 0))
+ break;
- rte_prefetch0(desc);
- sz = vq->desc[desc_indexes[i]].len / sizeof(*desc);
- idx = 0;
- } else {
- desc = vq->desc;
- sz = vq->size;
- idx = desc_indexes[i];
- }
+ if (likely(dev->dequeue_zero_copy == 0))
+ update_shadow_used_ring_split(vq, head_idx, 0);
- pkts[i] = rte_pktmbuf_alloc(mbuf_pool);
- if (unlikely(pkts[i] == NULL)) {
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
+ pkts[i] = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
+ if (unlikely(pkts[i] == NULL))
break;
- }
- err = copy_desc_to_mbuf(dev, vq, desc, sz, pkts[i], idx,
- mbuf_pool);
+ err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, pkts[i],
+ mbuf_pool);
if (unlikely(err)) {
rte_pktmbuf_free(pkts[i]);
break;
break;
}
zmbuf->mbuf = pkts[i];
- zmbuf->desc_idx = desc_indexes[i];
+ zmbuf->desc_idx = head_idx;
/*
* Pin lock the mbuf; we will check later to see
if (likely(dev->dequeue_zero_copy == 0)) {
do_data_copy_dequeue(vq);
- vq->last_used_idx += i;
- update_used_idx(dev, vq, i);
+ if (unlikely(i < count))
+ vq->shadow_used_idx = i;
+ if (likely(vq->shadow_used_idx)) {
+ flush_shadow_used_ring_split(dev, vq);
+ vhost_vring_call_split(dev, vq);
+ }
+ }
+
+ return i;
+}
+
+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,
+ uint16_t *ids)
+{
+ bool wrap = vq->avail_wrap_counter;
+ struct vring_packed_desc *descs = vq->desc_packed;
+ struct virtio_net_hdr *hdr;
+ uint64_t lens[PACKED_BATCH_SIZE];
+ uint64_t buf_lens[PACKED_BATCH_SIZE];
+ uint32_t buf_offset = dev->vhost_hlen;
+ uint16_t flags, i;
+
+ if (unlikely(avail_idx & PACKED_BATCH_MASK))
+ return -1;
+ if (unlikely((avail_idx + PACKED_BATCH_SIZE) > vq->size))
+ return -1;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ flags = descs[avail_idx + i].flags;
+ if (unlikely((wrap != !!(flags & VRING_DESC_F_AVAIL)) ||
+ (wrap == !!(flags & VRING_DESC_F_USED)) ||
+ (flags & PACKED_DESC_SINGLE_DEQUEUE_FLAG)))
+ return -1;
+ }
+
+ rte_smp_rmb();
+
+ 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) {
+ 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;
+ }
+
+ 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;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ buf_lens[i] = pkts[i]->buf_len - pkts[i]->data_off;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (unlikely(buf_lens[i] < (lens[i] - buf_offset)))
+ goto free_buf;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ pkts[i]->pkt_len = descs[avail_idx + i].len - buf_offset;
+ pkts[i]->data_len = pkts[i]->pkt_len;
+ ids[i] = descs[avail_idx + i].id;
+ }
+
+ 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]);
+ }
+ }
+
+ return 0;
+
+free_buf:
+ for (i = 0; i < PACKED_BATCH_SIZE; i++)
+ rte_pktmbuf_free(pkts[i]);
+
+ 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)
+{
+ uint16_t avail_idx = vq->last_avail_idx;
+ uint32_t buf_offset = dev->vhost_hlen;
+ uintptr_t desc_addrs[PACKED_BATCH_SIZE];
+ 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))
+ return -1;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ rte_prefetch0((void *)(uintptr_t)desc_addrs[i]);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ rte_memcpy(rte_pktmbuf_mtod_offset(pkts[i], void *, 0),
+ (void *)(uintptr_t)(desc_addrs[i] + buf_offset),
+ pkts[i]->pkt_len);
+
+ if (virtio_net_is_inorder(dev))
+ vhost_shadow_dequeue_batch_packed_inorder(vq,
+ ids[PACKED_BATCH_SIZE - 1]);
+ else
+ vhost_shadow_dequeue_batch_packed(dev, vq, ids);
+
+ vq_inc_last_avail_packed(vq, PACKED_BATCH_SIZE);
+
+ return 0;
+}
+
+static __rte_always_inline int
+vhost_dequeue_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts,
+ uint16_t *buf_id,
+ uint16_t *desc_count)
+{
+ struct buf_vector buf_vec[BUF_VECTOR_MAX];
+ uint32_t buf_len;
+ uint16_t nr_vec = 0;
+ int err;
+
+ if (unlikely(fill_vec_buf_packed(dev, vq,
+ vq->last_avail_idx, desc_count,
+ buf_vec, &nr_vec,
+ buf_id, &buf_len,
+ VHOST_ACCESS_RO) < 0))
+ return -1;
+
+ *pkts = virtio_dev_pktmbuf_alloc(dev, mbuf_pool, buf_len);
+ if (unlikely(*pkts == NULL)) {
+ VHOST_LOG_DATA(ERR,
+ "Failed to allocate memory for mbuf.\n");
+ return -1;
+ }
+
+ err = copy_desc_to_mbuf(dev, vq, buf_vec, nr_vec, *pkts,
+ mbuf_pool);
+ if (unlikely(err)) {
+ rte_pktmbuf_free(*pkts);
+ return -1;
}
+ return 0;
+}
+
+static __rte_always_inline int
+virtio_dev_tx_single_packed(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts)
+{
+
+ uint16_t buf_id, desc_count;
+
+ if (vhost_dequeue_single_packed(dev, vq, mbuf_pool, pkts, &buf_id,
+ &desc_count))
+ return -1;
+
+ if (virtio_net_is_inorder(dev))
+ vhost_shadow_dequeue_single_packed_inorder(vq, buf_id,
+ desc_count);
+ else
+ vhost_shadow_dequeue_single_packed(vq, buf_id, desc_count);
+
+ vq_inc_last_avail_packed(vq, desc_count);
+
+ return 0;
+}
+
+static __rte_always_inline int
+virtio_dev_tx_batch_packed_zmbuf(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts)
+{
+ struct zcopy_mbuf *zmbufs[PACKED_BATCH_SIZE];
+ uintptr_t desc_addrs[PACKED_BATCH_SIZE];
+ uint16_t ids[PACKED_BATCH_SIZE];
+ uint16_t i;
+
+ uint16_t avail_idx = vq->last_avail_idx;
+
+ if (vhost_reserve_avail_batch_packed(dev, vq, mbuf_pool, pkts,
+ avail_idx, desc_addrs, ids))
+ return -1;
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ zmbufs[i] = get_zmbuf(vq);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ if (!zmbufs[i])
+ goto free_pkt;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) {
+ zmbufs[i]->mbuf = pkts[i];
+ zmbufs[i]->desc_idx = ids[i];
+ zmbufs[i]->desc_count = 1;
+ }
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ rte_mbuf_refcnt_update(pkts[i], 1);
+
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbufs[i], next);
+
+ vq->nr_zmbuf += PACKED_BATCH_SIZE;
+ vq_inc_last_avail_packed(vq, PACKED_BATCH_SIZE);
+
+ return 0;
+
+free_pkt:
+ vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
+ rte_pktmbuf_free(pkts[i]);
+
+ return -1;
+}
+
+static __rte_always_inline int
+virtio_dev_tx_single_packed_zmbuf(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts)
+{
+ uint16_t buf_id, desc_count;
+ struct zcopy_mbuf *zmbuf;
+
+ if (vhost_dequeue_single_packed(dev, vq, mbuf_pool, pkts, &buf_id,
+ &desc_count))
+ return -1;
+
+ zmbuf = get_zmbuf(vq);
+ if (!zmbuf) {
+ rte_pktmbuf_free(*pkts);
+ return -1;
+ }
+ zmbuf->mbuf = *pkts;
+ zmbuf->desc_idx = buf_id;
+ zmbuf->desc_count = desc_count;
+
+ rte_mbuf_refcnt_update(*pkts, 1);
+
+ vq->nr_zmbuf += 1;
+ TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next);
+
+ vq_inc_last_avail_packed(vq, desc_count);
+ return 0;
+}
+
+static __rte_always_inline void
+free_zmbuf(struct vhost_virtqueue *vq)
+{
+ struct zcopy_mbuf *next = NULL;
+ struct zcopy_mbuf *zmbuf;
+
+ for (zmbuf = TAILQ_FIRST(&vq->zmbuf_list);
+ zmbuf != NULL; zmbuf = next) {
+ next = TAILQ_NEXT(zmbuf, next);
+
+ uint16_t last_used_idx = vq->last_used_idx;
+
+ if (mbuf_is_consumed(zmbuf->mbuf)) {
+ uint16_t flags;
+ flags = vq->desc_packed[last_used_idx].flags;
+ 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;
+ }
+
+ vq->desc_packed[last_used_idx].id = zmbuf->desc_idx;
+ vq->desc_packed[last_used_idx].len = 0;
+
+ rte_smp_wmb();
+ vq->desc_packed[last_used_idx].flags = flags;
+
+ vq_inc_last_used_packed(vq, zmbuf->desc_count);
+
+ TAILQ_REMOVE(&vq->zmbuf_list, zmbuf, next);
+ restore_mbuf(zmbuf->mbuf);
+ rte_pktmbuf_free(zmbuf->mbuf);
+ put_zmbuf(zmbuf);
+ vq->nr_zmbuf -= 1;
+ }
+ }
+}
+
+static __rte_noinline uint16_t
+virtio_dev_tx_packed_zmbuf(struct virtio_net *dev,
+ struct vhost_virtqueue *vq,
+ struct rte_mempool *mbuf_pool,
+ struct rte_mbuf **pkts,
+ uint32_t count)
+{
+ uint32_t pkt_idx = 0;
+ uint32_t remained = count;
+
+ free_zmbuf(vq);
+
+ do {
+ if (remained >= PACKED_BATCH_SIZE) {
+ if (!virtio_dev_tx_batch_packed_zmbuf(dev, vq,
+ mbuf_pool, &pkts[pkt_idx])) {
+ pkt_idx += PACKED_BATCH_SIZE;
+ remained -= PACKED_BATCH_SIZE;
+ continue;
+ }
+ }
+
+ if (virtio_dev_tx_single_packed_zmbuf(dev, vq, mbuf_pool,
+ &pkts[pkt_idx]))
+ break;
+ pkt_idx++;
+ remained--;
+
+ } while (remained);
+
+ if (pkt_idx)
+ vhost_vring_call_packed(dev, vq);
+
+ return pkt_idx;
+}
+
+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,
+ 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_tx_batch_packed(dev, vq, mbuf_pool,
+ &pkts[pkt_idx])) {
+ pkt_idx += PACKED_BATCH_SIZE;
+ remained -= PACKED_BATCH_SIZE;
+ continue;
+ }
+ }
+
+ if (virtio_dev_tx_single_packed(dev, vq, mbuf_pool,
+ &pkts[pkt_idx]))
+ break;
+ pkt_idx++;
+ remained--;
+
+ } while (remained);
+
+ if (vq->shadow_used_idx) {
+ do_data_copy_dequeue(vq);
+
+ vhost_flush_dequeue_shadow_packed(dev, vq);
+ vhost_vring_call_packed(dev, vq);
+ }
+
+ return pkt_idx;
+}
+
+uint16_t
+rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
+ struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count)
+{
+ struct virtio_net *dev;
+ struct rte_mbuf *rarp_mbuf = NULL;
+ struct vhost_virtqueue *vq;
+ int16_t success = 1;
+
+ dev = get_device(vid);
+ if (!dev)
+ return 0;
+
+ if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) {
+ VHOST_LOG_DATA(ERR,
+ "(%d) %s: built-in vhost net backend is disabled.\n",
+ dev->vid, __func__);
+ return 0;
+ }
+
+ if (unlikely(!is_valid_virt_queue_idx(queue_id, 1, 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(rte_spinlock_trylock(&vq->access_lock) == 0))
+ return 0;
+
+ if (unlikely(vq->enabled == 0)) {
+ count = 0;
+ goto out_access_unlock;
+ }
+
+ if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
+ vhost_user_iotlb_rd_lock(vq);
+
+ if (unlikely(vq->access_ok == 0))
+ if (unlikely(vring_translate(dev, vq) < 0)) {
+ count = 0;
+ goto out;
+ }
+
+ /*
+ * Construct a RARP broadcast packet, and inject it to the "pkts"
+ * array, to looks like that guest actually send such packet.
+ *
+ * Check user_send_rarp() for more information.
+ *
+ * broadcast_rarp shares a cacheline in the virtio_net structure
+ * with some fields that are accessed during enqueue and
+ * __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 compare and exchange if the read indicates it
+ * is likely to be set.
+ */
+ 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) {
+ VHOST_LOG_DATA(ERR, "Failed to make RARP packet.\n");
+ count = 0;
+ goto out;
+ }
+ count -= 1;
+ }
+
+ if (vq_is_packed(dev)) {
+ if (unlikely(dev->dequeue_zero_copy))
+ count = virtio_dev_tx_packed_zmbuf(dev, vq, mbuf_pool,
+ pkts, count);
+ else
+ count = virtio_dev_tx_packed(dev, vq, mbuf_pool, pkts,
+ count);
+ } else
+ count = virtio_dev_tx_split(dev, vq, mbuf_pool, pkts, count);
+
out:
if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))
vhost_user_iotlb_rd_unlock(vq);
+out_access_unlock:
+ rte_spinlock_unlock(&vq->access_lock);
+
if (unlikely(rarp_mbuf != NULL)) {
/*
* Inject it to the head of "pkts" array, so that switch's mac
* learning table will get updated first.
*/
- memmove(&pkts[1], pkts, i * sizeof(struct rte_mbuf *));
+ memmove(&pkts[1], pkts, count * sizeof(struct rte_mbuf *));
pkts[0] = rarp_mbuf;
- i += 1;
+ count += 1;
}
- return i;
+ return count;
}