X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_rxtx.c;h=f915b8a2c993a4131b2dfa696cbe01950c1c3b46;hb=28b0514504cf0f71f822f0aed5aacc83eb8ada12;hp=cb8f89f185b169fcfd40b2be4659170ca684d6d6;hpb=81e5cdf19e583c742040d3be83b8cc79b451e243;p=dpdk.git diff --git a/drivers/net/virtio/virtio_rxtx.c b/drivers/net/virtio/virtio_rxtx.c index cb8f89f185..f915b8a2c9 100644 --- a/drivers/net/virtio/virtio_rxtx.c +++ b/drivers/net/virtio/virtio_rxtx.c @@ -31,6 +31,7 @@ #include "virtqueue.h" #include "virtio_rxtx.h" #include "virtio_rxtx_simple.h" +#include "virtio_ring.h" #ifdef RTE_LIBRTE_VIRTIO_DEBUG_DUMP #define VIRTIO_DUMP_PACKET(m, len) rte_pktmbuf_dump(stdout, m, len) @@ -44,7 +45,7 @@ virtio_dev_rx_queue_done(void *rxq, uint16_t offset) struct virtnet_rx *rxvq = rxq; struct virtqueue *vq = rxvq->vq; - return VIRTQUEUE_NUSED(vq) >= offset; + return virtqueue_nused(vq) >= offset; } void @@ -61,13 +62,13 @@ vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx) struct vq_desc_extra *dxp; uint16_t desc_idx_last = desc_idx; - dp = &vq->vq_ring.desc[desc_idx]; + dp = &vq->vq_split.ring.desc[desc_idx]; dxp = &vq->vq_descx[desc_idx]; vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt + dxp->ndescs); if ((dp->flags & VRING_DESC_F_INDIRECT) == 0) { while (dp->flags & VRING_DESC_F_NEXT) { desc_idx_last = dp->next; - dp = &vq->vq_ring.desc[dp->next]; + dp = &vq->vq_split.ring.desc[dp->next]; } } dxp->ndescs = 0; @@ -80,7 +81,7 @@ vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx) if (vq->vq_desc_tail_idx == VQ_RING_DESC_CHAIN_END) { vq->vq_desc_head_idx = desc_idx; } else { - dp_tail = &vq->vq_ring.desc[vq->vq_desc_tail_idx]; + dp_tail = &vq->vq_split.ring.desc[vq->vq_desc_tail_idx]; dp_tail->next = desc_idx; } @@ -88,6 +89,92 @@ vq_ring_free_chain(struct virtqueue *vq, uint16_t desc_idx) dp->next = VQ_RING_DESC_CHAIN_END; } +void +virtio_update_packet_stats(struct virtnet_stats *stats, struct rte_mbuf *mbuf) +{ + uint32_t s = mbuf->pkt_len; + struct rte_ether_addr *ea; + + stats->bytes += s; + + if (s == 64) { + stats->size_bins[1]++; + } else if (s > 64 && s < 1024) { + uint32_t bin; + + /* count zeros, and offset into correct bin */ + bin = (sizeof(s) * 8) - __builtin_clz(s) - 5; + stats->size_bins[bin]++; + } else { + if (s < 64) + stats->size_bins[0]++; + else if (s < 1519) + stats->size_bins[6]++; + else + stats->size_bins[7]++; + } + + ea = rte_pktmbuf_mtod(mbuf, struct rte_ether_addr *); + if (rte_is_multicast_ether_addr(ea)) { + if (rte_is_broadcast_ether_addr(ea)) + stats->broadcast++; + else + stats->multicast++; + } +} + +static inline void +virtio_rx_stats_updated(struct virtnet_rx *rxvq, struct rte_mbuf *m) +{ + VIRTIO_DUMP_PACKET(m, m->data_len); + + virtio_update_packet_stats(&rxvq->stats, m); +} + +static uint16_t +virtqueue_dequeue_burst_rx_packed(struct virtqueue *vq, + struct rte_mbuf **rx_pkts, + uint32_t *len, + uint16_t num) +{ + struct rte_mbuf *cookie; + uint16_t used_idx; + uint16_t id; + struct vring_packed_desc *desc; + uint16_t i; + + desc = vq->vq_packed.ring.desc; + + for (i = 0; i < num; i++) { + used_idx = vq->vq_used_cons_idx; + /* desc_is_used has a load-acquire or rte_cio_rmb inside + * and wait for used desc in virtqueue. + */ + if (!desc_is_used(&desc[used_idx], vq)) + return i; + len[i] = desc[used_idx].len; + id = desc[used_idx].id; + cookie = (struct rte_mbuf *)vq->vq_descx[id].cookie; + if (unlikely(cookie == NULL)) { + PMD_DRV_LOG(ERR, "vring descriptor with no mbuf cookie at %u", + vq->vq_used_cons_idx); + break; + } + rte_prefetch0(cookie); + rte_packet_prefetch(rte_pktmbuf_mtod(cookie, void *)); + rx_pkts[i] = cookie; + + vq->vq_free_cnt++; + vq->vq_used_cons_idx++; + if (vq->vq_used_cons_idx >= vq->vq_nentries) { + vq->vq_used_cons_idx -= vq->vq_nentries; + vq->vq_packed.used_wrap_counter ^= 1; + } + } + + return i; +} + static uint16_t virtqueue_dequeue_burst_rx(struct virtqueue *vq, struct rte_mbuf **rx_pkts, uint32_t *len, uint16_t num) @@ -100,7 +187,7 @@ virtqueue_dequeue_burst_rx(struct virtqueue *vq, struct rte_mbuf **rx_pkts, /* Caller does the check */ for (i = 0; i < num ; i++) { used_idx = (uint16_t)(vq->vq_used_cons_idx & (vq->vq_nentries - 1)); - uep = &vq->vq_ring.used->ring[used_idx]; + uep = &vq->vq_split.ring.used->ring[used_idx]; desc_idx = (uint16_t) uep->id; len[i] = uep->len; cookie = (struct rte_mbuf *)vq->vq_descx[desc_idx].cookie; @@ -139,7 +226,7 @@ virtqueue_dequeue_rx_inorder(struct virtqueue *vq, for (i = 0; i < num; i++) { used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1); /* Desc idx same as used idx */ - uep = &vq->vq_ring.used->ring[used_idx]; + uep = &vq->vq_split.ring.used->ring[used_idx]; len[i] = uep->len; cookie = (struct rte_mbuf *)vq->vq_descx[used_idx].cookie; @@ -160,69 +247,6 @@ virtqueue_dequeue_rx_inorder(struct virtqueue *vq, return i; } -#ifndef DEFAULT_TX_FREE_THRESH -#define DEFAULT_TX_FREE_THRESH 32 -#endif - -/* Cleanup from completed transmits. */ -static void -virtio_xmit_cleanup(struct virtqueue *vq, uint16_t num) -{ - uint16_t i, used_idx, desc_idx; - for (i = 0; i < num; i++) { - struct vring_used_elem *uep; - struct vq_desc_extra *dxp; - - used_idx = (uint16_t)(vq->vq_used_cons_idx & (vq->vq_nentries - 1)); - uep = &vq->vq_ring.used->ring[used_idx]; - - desc_idx = (uint16_t) uep->id; - dxp = &vq->vq_descx[desc_idx]; - vq->vq_used_cons_idx++; - vq_ring_free_chain(vq, desc_idx); - - if (dxp->cookie != NULL) { - rte_pktmbuf_free(dxp->cookie); - dxp->cookie = NULL; - } - } -} - -/* Cleanup from completed inorder transmits. */ -static void -virtio_xmit_cleanup_inorder(struct virtqueue *vq, uint16_t num) -{ - uint16_t i, used_idx, desc_idx = 0, last_idx; - int16_t free_cnt = 0; - struct vq_desc_extra *dxp = NULL; - - if (unlikely(num == 0)) - return; - - for (i = 0; i < num; i++) { - struct vring_used_elem *uep; - - used_idx = vq->vq_used_cons_idx & (vq->vq_nentries - 1); - uep = &vq->vq_ring.used->ring[used_idx]; - desc_idx = (uint16_t)uep->id; - - dxp = &vq->vq_descx[desc_idx]; - vq->vq_used_cons_idx++; - - if (dxp->cookie != NULL) { - rte_pktmbuf_free(dxp->cookie); - dxp->cookie = NULL; - } - } - - last_idx = desc_idx + dxp->ndescs - 1; - free_cnt = last_idx - vq->vq_desc_tail_idx; - if (free_cnt <= 0) - free_cnt += vq->vq_nentries; - - vq_ring_free_inorder(vq, last_idx, free_cnt); -} - static inline int virtqueue_enqueue_refill_inorder(struct virtqueue *vq, struct rte_mbuf **cookies, @@ -239,7 +263,7 @@ virtqueue_enqueue_refill_inorder(struct virtqueue *vq, return -EMSGSIZE; head_idx = vq->vq_desc_head_idx & (vq->vq_nentries - 1); - start_dp = vq->vq_ring.desc; + start_dp = vq->vq_split.ring.desc; while (i < num) { idx = head_idx & (vq->vq_nentries - 1); @@ -267,42 +291,90 @@ virtqueue_enqueue_refill_inorder(struct virtqueue *vq, } static inline int -virtqueue_enqueue_recv_refill(struct virtqueue *vq, struct rte_mbuf *cookie) +virtqueue_enqueue_recv_refill(struct virtqueue *vq, struct rte_mbuf **cookie, + uint16_t num) { struct vq_desc_extra *dxp; struct virtio_hw *hw = vq->hw; - struct vring_desc *start_dp; - uint16_t needed = 1; - uint16_t head_idx, idx; + struct vring_desc *start_dp = vq->vq_split.ring.desc; + uint16_t idx, i; if (unlikely(vq->vq_free_cnt == 0)) return -ENOSPC; - if (unlikely(vq->vq_free_cnt < needed)) + if (unlikely(vq->vq_free_cnt < num)) return -EMSGSIZE; - head_idx = vq->vq_desc_head_idx; - if (unlikely(head_idx >= vq->vq_nentries)) + if (unlikely(vq->vq_desc_head_idx >= vq->vq_nentries)) return -EFAULT; - idx = head_idx; - dxp = &vq->vq_descx[idx]; - dxp->cookie = (void *)cookie; - dxp->ndescs = needed; + for (i = 0; i < num; i++) { + idx = vq->vq_desc_head_idx; + dxp = &vq->vq_descx[idx]; + dxp->cookie = (void *)cookie[i]; + dxp->ndescs = 1; - start_dp = vq->vq_ring.desc; - start_dp[idx].addr = - VIRTIO_MBUF_ADDR(cookie, vq) + - RTE_PKTMBUF_HEADROOM - hw->vtnet_hdr_size; - start_dp[idx].len = - cookie->buf_len - RTE_PKTMBUF_HEADROOM + hw->vtnet_hdr_size; - start_dp[idx].flags = VRING_DESC_F_WRITE; - idx = start_dp[idx].next; - vq->vq_desc_head_idx = idx; - if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END) - vq->vq_desc_tail_idx = idx; - vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - needed); - vq_update_avail_ring(vq, head_idx); + start_dp[idx].addr = + VIRTIO_MBUF_ADDR(cookie[i], vq) + + RTE_PKTMBUF_HEADROOM - hw->vtnet_hdr_size; + start_dp[idx].len = + cookie[i]->buf_len - RTE_PKTMBUF_HEADROOM + + hw->vtnet_hdr_size; + start_dp[idx].flags = VRING_DESC_F_WRITE; + vq->vq_desc_head_idx = start_dp[idx].next; + vq_update_avail_ring(vq, idx); + if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END) { + vq->vq_desc_tail_idx = vq->vq_desc_head_idx; + break; + } + } + + vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - num); + + return 0; +} + +static inline int +virtqueue_enqueue_recv_refill_packed(struct virtqueue *vq, + struct rte_mbuf **cookie, uint16_t num) +{ + struct vring_packed_desc *start_dp = vq->vq_packed.ring.desc; + uint16_t flags = vq->vq_packed.cached_flags; + struct virtio_hw *hw = vq->hw; + struct vq_desc_extra *dxp; + uint16_t idx; + int i; + + if (unlikely(vq->vq_free_cnt == 0)) + return -ENOSPC; + if (unlikely(vq->vq_free_cnt < num)) + return -EMSGSIZE; + + for (i = 0; i < num; i++) { + idx = vq->vq_avail_idx; + dxp = &vq->vq_descx[idx]; + dxp->cookie = (void *)cookie[i]; + dxp->ndescs = 1; + + start_dp[idx].addr = VIRTIO_MBUF_ADDR(cookie[i], vq) + + RTE_PKTMBUF_HEADROOM - hw->vtnet_hdr_size; + start_dp[idx].len = cookie[i]->buf_len - RTE_PKTMBUF_HEADROOM + + hw->vtnet_hdr_size; + + vq->vq_desc_head_idx = dxp->next; + if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END) + vq->vq_desc_tail_idx = vq->vq_desc_head_idx; + + virtqueue_store_flags_packed(&start_dp[idx], flags, + hw->weak_barriers); + if (++vq->vq_avail_idx >= vq->vq_nentries) { + vq->vq_avail_idx -= vq->vq_nentries; + vq->vq_packed.cached_flags ^= + VRING_PACKED_DESC_F_AVAIL_USED; + flags = vq->vq_packed.cached_flags; + } + } + vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - num); return 0; } @@ -316,13 +388,14 @@ virtio_tso_fix_cksum(struct rte_mbuf *m) /* common case: header is not fragmented */ if (likely(rte_pktmbuf_data_len(m) >= m->l2_len + m->l3_len + m->l4_len)) { - struct ipv4_hdr *iph; - struct ipv6_hdr *ip6h; - struct tcp_hdr *th; + struct rte_ipv4_hdr *iph; + struct rte_ipv6_hdr *ip6h; + struct rte_tcp_hdr *th; uint16_t prev_cksum, new_cksum, ip_len, ip_paylen; uint32_t tmp; - iph = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *, m->l2_len); + iph = rte_pktmbuf_mtod_offset(m, + struct rte_ipv4_hdr *, m->l2_len); th = RTE_PTR_ADD(iph, m->l3_len); if ((iph->version_ihl >> 4) == 4) { iph->hdr_checksum = 0; @@ -331,7 +404,7 @@ virtio_tso_fix_cksum(struct rte_mbuf *m) ip_paylen = rte_cpu_to_be_16(rte_be_to_cpu_16(ip_len) - m->l3_len); } else { - ip6h = (struct ipv6_hdr *)iph; + ip6h = (struct rte_ipv6_hdr *)iph; ip_paylen = ip6h->payload_len; } @@ -348,60 +421,7 @@ virtio_tso_fix_cksum(struct rte_mbuf *m) } -/* avoid write operation when necessary, to lessen cache issues */ -#define ASSIGN_UNLESS_EQUAL(var, val) do { \ - if ((var) != (val)) \ - (var) = (val); \ -} while (0) - -static inline void -virtqueue_xmit_offload(struct virtio_net_hdr *hdr, - struct rte_mbuf *cookie, - bool offload) -{ - if (offload) { - if (cookie->ol_flags & PKT_TX_TCP_SEG) - cookie->ol_flags |= PKT_TX_TCP_CKSUM; - - switch (cookie->ol_flags & PKT_TX_L4_MASK) { - case PKT_TX_UDP_CKSUM: - hdr->csum_start = cookie->l2_len + cookie->l3_len; - hdr->csum_offset = offsetof(struct udp_hdr, - dgram_cksum); - hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - break; - - case PKT_TX_TCP_CKSUM: - hdr->csum_start = cookie->l2_len + cookie->l3_len; - hdr->csum_offset = offsetof(struct tcp_hdr, cksum); - hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - break; - - default: - ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0); - ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0); - ASSIGN_UNLESS_EQUAL(hdr->flags, 0); - break; - } - /* TCP Segmentation Offload */ - if (cookie->ol_flags & PKT_TX_TCP_SEG) { - virtio_tso_fix_cksum(cookie); - hdr->gso_type = (cookie->ol_flags & PKT_TX_IPV6) ? - VIRTIO_NET_HDR_GSO_TCPV6 : - VIRTIO_NET_HDR_GSO_TCPV4; - hdr->gso_size = cookie->tso_segsz; - hdr->hdr_len = - cookie->l2_len + - cookie->l3_len + - cookie->l4_len; - } else { - ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0); - ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0); - ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0); - } - } -} static inline void virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq, @@ -413,39 +433,34 @@ virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq, struct vring_desc *start_dp; struct virtio_net_hdr *hdr; uint16_t idx; - uint16_t head_size = vq->hw->vtnet_hdr_size; + int16_t head_size = vq->hw->vtnet_hdr_size; uint16_t i = 0; idx = vq->vq_desc_head_idx; - start_dp = vq->vq_ring.desc; + start_dp = vq->vq_split.ring.desc; while (i < num) { idx = idx & (vq->vq_nentries - 1); - dxp = &vq->vq_descx[idx]; + dxp = &vq->vq_descx[vq->vq_avail_idx & (vq->vq_nentries - 1)]; dxp->cookie = (void *)cookies[i]; dxp->ndescs = 1; + virtio_update_packet_stats(&txvq->stats, cookies[i]); - hdr = (struct virtio_net_hdr *) - rte_pktmbuf_prepend(cookies[i], head_size); - cookies[i]->pkt_len -= head_size; - - /* if offload disabled, it is not zeroed below, do it now */ - if (!vq->hw->has_tx_offload) { - ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0); - ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0); - ASSIGN_UNLESS_EQUAL(hdr->flags, 0); - ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0); - ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0); - ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0); - } + hdr = rte_pktmbuf_mtod_offset(cookies[i], + struct virtio_net_hdr *, -head_size); - virtqueue_xmit_offload(hdr, cookies[i], - vq->hw->has_tx_offload); + /* if offload disabled, hdr is not zeroed yet, do it now */ + if (!vq->hw->has_tx_offload) + virtqueue_clear_net_hdr(hdr); + else + virtqueue_xmit_offload(hdr, cookies[i], true); - start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq); - start_dp[idx].len = cookies[i]->data_len; + start_dp[idx].addr = + VIRTIO_MBUF_DATA_DMA_ADDR(cookies[i], vq) - head_size; + start_dp[idx].len = cookies[i]->data_len + head_size; start_dp[idx].flags = 0; + vq_update_avail_ring(vq, idx); idx++; @@ -456,6 +471,58 @@ virtqueue_enqueue_xmit_inorder(struct virtnet_tx *txvq, vq->vq_desc_head_idx = idx & (vq->vq_nentries - 1); } +static inline void +virtqueue_enqueue_xmit_packed_fast(struct virtnet_tx *txvq, + struct rte_mbuf *cookie, + int in_order) +{ + struct virtqueue *vq = txvq->vq; + struct vring_packed_desc *dp; + struct vq_desc_extra *dxp; + uint16_t idx, id, flags; + int16_t head_size = vq->hw->vtnet_hdr_size; + struct virtio_net_hdr *hdr; + + id = in_order ? vq->vq_avail_idx : vq->vq_desc_head_idx; + idx = vq->vq_avail_idx; + dp = &vq->vq_packed.ring.desc[idx]; + + dxp = &vq->vq_descx[id]; + dxp->ndescs = 1; + dxp->cookie = cookie; + + flags = vq->vq_packed.cached_flags; + + /* prepend cannot fail, checked by caller */ + hdr = rte_pktmbuf_mtod_offset(cookie, struct virtio_net_hdr *, + -head_size); + + /* if offload disabled, hdr is not zeroed yet, do it now */ + if (!vq->hw->has_tx_offload) + virtqueue_clear_net_hdr(hdr); + else + virtqueue_xmit_offload(hdr, cookie, true); + + dp->addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq) - head_size; + dp->len = cookie->data_len + head_size; + dp->id = id; + + if (++vq->vq_avail_idx >= vq->vq_nentries) { + vq->vq_avail_idx -= vq->vq_nentries; + vq->vq_packed.cached_flags ^= VRING_PACKED_DESC_F_AVAIL_USED; + } + + vq->vq_free_cnt--; + + if (!in_order) { + vq->vq_desc_head_idx = dxp->next; + if (vq->vq_desc_head_idx == VQ_RING_DESC_CHAIN_END) + vq->vq_desc_tail_idx = VQ_RING_DESC_CHAIN_END; + } + + virtqueue_store_flags_packed(dp, flags, vq->hw->weak_barriers); +} + static inline void virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie, uint16_t needed, int use_indirect, int can_push, @@ -467,35 +534,30 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie, struct vring_desc *start_dp; uint16_t seg_num = cookie->nb_segs; uint16_t head_idx, idx; - uint16_t head_size = vq->hw->vtnet_hdr_size; + int16_t head_size = vq->hw->vtnet_hdr_size; + bool prepend_header = false; struct virtio_net_hdr *hdr; head_idx = vq->vq_desc_head_idx; idx = head_idx; - dxp = &vq->vq_descx[idx]; + if (in_order) + dxp = &vq->vq_descx[vq->vq_avail_idx & (vq->vq_nentries - 1)]; + else + dxp = &vq->vq_descx[idx]; dxp->cookie = (void *)cookie; dxp->ndescs = needed; - start_dp = vq->vq_ring.desc; + start_dp = vq->vq_split.ring.desc; if (can_push) { /* prepend cannot fail, checked by caller */ - hdr = (struct virtio_net_hdr *) - rte_pktmbuf_prepend(cookie, head_size); - /* rte_pktmbuf_prepend() counts the hdr size to the pkt length, - * which is wrong. Below subtract restores correct pkt size. - */ - cookie->pkt_len -= head_size; + hdr = rte_pktmbuf_mtod_offset(cookie, struct virtio_net_hdr *, + -head_size); + prepend_header = true; /* if offload disabled, it is not zeroed below, do it now */ - if (!vq->hw->has_tx_offload) { - ASSIGN_UNLESS_EQUAL(hdr->csum_start, 0); - ASSIGN_UNLESS_EQUAL(hdr->csum_offset, 0); - ASSIGN_UNLESS_EQUAL(hdr->flags, 0); - ASSIGN_UNLESS_EQUAL(hdr->gso_type, 0); - ASSIGN_UNLESS_EQUAL(hdr->gso_size, 0); - ASSIGN_UNLESS_EQUAL(hdr->hdr_len, 0); - } + if (!vq->hw->has_tx_offload) + virtqueue_clear_net_hdr(hdr); } else if (use_indirect) { /* setup tx ring slot to point to indirect * descriptor list stored in reserved region. @@ -530,12 +592,17 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq, struct rte_mbuf *cookie, do { start_dp[idx].addr = VIRTIO_MBUF_DATA_DMA_ADDR(cookie, vq); start_dp[idx].len = cookie->data_len; + if (prepend_header) { + start_dp[idx].addr -= head_size; + start_dp[idx].len += head_size; + prepend_header = false; + } start_dp[idx].flags = cookie->next ? VRING_DESC_F_NEXT : 0; idx = start_dp[idx].next; } while ((cookie = cookie->next) != NULL); if (use_indirect) - idx = vq->vq_ring.desc[head_idx].next; + idx = vq->vq_split.ring.desc[head_idx].next; vq->vq_free_cnt = (uint16_t)(vq->vq_free_cnt - needed); @@ -564,16 +631,44 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx, uint16_t nb_desc, unsigned int socket_id __rte_unused, - const struct rte_eth_rxconf *rx_conf __rte_unused, + const struct rte_eth_rxconf *rx_conf, struct rte_mempool *mp) { uint16_t vtpci_queue_idx = 2 * queue_idx + VTNET_SQ_RQ_QUEUE_IDX; struct virtio_hw *hw = dev->data->dev_private; struct virtqueue *vq = hw->vqs[vtpci_queue_idx]; struct virtnet_rx *rxvq; + uint16_t rx_free_thresh; PMD_INIT_FUNC_TRACE(); + if (rx_conf->rx_deferred_start) { + PMD_INIT_LOG(ERR, "Rx deferred start is not supported"); + return -EINVAL; + } + + rx_free_thresh = rx_conf->rx_free_thresh; + if (rx_free_thresh == 0) + rx_free_thresh = + RTE_MIN(vq->vq_nentries / 4, DEFAULT_RX_FREE_THRESH); + + if (rx_free_thresh & 0x3) { + RTE_LOG(ERR, PMD, "rx_free_thresh must be multiples of four." + " (rx_free_thresh=%u port=%u queue=%u)\n", + rx_free_thresh, dev->data->port_id, queue_idx); + return -EINVAL; + } + + if (rx_free_thresh >= vq->vq_nentries) { + RTE_LOG(ERR, PMD, "rx_free_thresh must be less than the " + "number of RX entries (%u)." + " (rx_free_thresh=%u port=%u queue=%u)\n", + vq->vq_nentries, + rx_free_thresh, dev->data->port_id, queue_idx); + return -EINVAL; + } + vq->vq_free_thresh = rx_free_thresh; + if (nb_desc == 0 || nb_desc > vq->vq_nentries) nb_desc = vq->vq_nentries; vq->vq_free_cnt = RTE_MIN(vq->vq_free_cnt, nb_desc); @@ -581,11 +676,6 @@ virtio_dev_rx_queue_setup(struct rte_eth_dev *dev, rxvq = &vq->rxq; rxvq->queue_id = queue_idx; rxvq->mpool = mp; - if (rxvq->mpool == NULL) { - rte_exit(EXIT_FAILURE, - "Cannot allocate mbufs for rx virtqueue"); - } - dev->data->rx_queues[queue_idx] = rxvq; return 0; @@ -601,17 +691,18 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx) struct rte_mbuf *m; uint16_t desc_idx; int error, nbufs, i; + bool in_order = vtpci_with_feature(hw, VIRTIO_F_IN_ORDER); PMD_INIT_FUNC_TRACE(); /* Allocate blank mbufs for the each rx descriptor */ nbufs = 0; - if (hw->use_simple_rx) { + if (hw->use_vec_rx && !vtpci_packed_queue(hw)) { for (desc_idx = 0; desc_idx < vq->vq_nentries; desc_idx++) { - vq->vq_ring.avail->ring[desc_idx] = desc_idx; - vq->vq_ring.desc[desc_idx].flags = + vq->vq_split.ring.avail->ring[desc_idx] = desc_idx; + vq->vq_split.ring.desc[desc_idx].flags = VRING_DESC_F_WRITE; } @@ -625,12 +716,12 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx) &rxvq->fake_mbuf; } - if (hw->use_simple_rx) { + if (hw->use_vec_rx && !vtpci_packed_queue(hw)) { while (vq->vq_free_cnt >= RTE_VIRTIO_VPMD_RX_REARM_THRESH) { virtio_rxq_rearm_vec(rxvq); nbufs += RTE_VIRTIO_VPMD_RX_REARM_THRESH; } - } else if (hw->use_inorder_rx) { + } else if (!vtpci_packed_queue(vq->hw) && in_order) { if ((!virtqueue_full(vq))) { uint16_t free_cnt = vq->vq_free_cnt; struct rte_mbuf *pkts[free_cnt]; @@ -656,7 +747,12 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx) break; /* Enqueue allocated buffers */ - error = virtqueue_enqueue_recv_refill(vq, m); + if (vtpci_packed_queue(vq->hw)) + error = virtqueue_enqueue_recv_refill_packed(vq, + &m, 1); + else + error = virtqueue_enqueue_recv_refill(vq, + &m, 1); if (error) { rte_pktmbuf_free(m); break; @@ -664,7 +760,8 @@ virtio_dev_rx_queue_setup_finish(struct rte_eth_dev *dev, uint16_t queue_idx) nbufs++; } - vq_update_avail_idx(vq); + if (!vtpci_packed_queue(vq->hw)) + vq_update_avail_idx(vq); } PMD_INIT_LOG(DEBUG, "Allocated %d bufs", nbufs); @@ -696,6 +793,11 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev, PMD_INIT_FUNC_TRACE(); + if (tx_conf->tx_deferred_start) { + PMD_INIT_LOG(ERR, "Tx deferred start is not supported"); + return -EINVAL; + } + if (nb_desc == 0 || nb_desc > vq->vq_nentries) nb_desc = vq->vq_nentries; vq->vq_free_cnt = RTE_MIN(vq->vq_free_cnt, nb_desc); @@ -709,7 +811,7 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev, RTE_MIN(vq->vq_nentries / 4, DEFAULT_TX_FREE_THRESH); if (tx_free_thresh >= (vq->vq_nentries - 3)) { - RTE_LOG(ERR, PMD, "tx_free_thresh must be less than the " + PMD_DRV_LOG(ERR, "tx_free_thresh must be less than the " "number of TX entries minus 3 (%u)." " (tx_free_thresh=%u port=%u queue=%u)\n", vq->vq_nentries - 3, @@ -733,15 +835,17 @@ virtio_dev_tx_queue_setup_finish(struct rte_eth_dev *dev, PMD_INIT_FUNC_TRACE(); - if (hw->use_inorder_tx) - vq->vq_ring.desc[vq->vq_nentries - 1].next = 0; + if (!vtpci_packed_queue(hw)) { + if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) + vq->vq_split.ring.desc[vq->vq_nentries - 1].next = 0; + } VIRTQUEUE_DUMP(vq); return 0; } -static void +static inline void virtio_discard_rxbuf(struct virtqueue *vq, struct rte_mbuf *m) { int error; @@ -749,70 +853,31 @@ virtio_discard_rxbuf(struct virtqueue *vq, struct rte_mbuf *m) * Requeue the discarded mbuf. This should always be * successful since it was just dequeued. */ - error = virtqueue_enqueue_recv_refill(vq, m); + if (vtpci_packed_queue(vq->hw)) + error = virtqueue_enqueue_recv_refill_packed(vq, &m, 1); + else + error = virtqueue_enqueue_recv_refill(vq, &m, 1); if (unlikely(error)) { - RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf"); + PMD_DRV_LOG(ERR, "cannot requeue discarded mbuf"); rte_pktmbuf_free(m); } } -static void +static inline void virtio_discard_rxbuf_inorder(struct virtqueue *vq, struct rte_mbuf *m) { int error; error = virtqueue_enqueue_refill_inorder(vq, &m, 1); if (unlikely(error)) { - RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf"); + PMD_DRV_LOG(ERR, "cannot requeue discarded mbuf"); rte_pktmbuf_free(m); } } -static void -virtio_update_packet_stats(struct virtnet_stats *stats, struct rte_mbuf *mbuf) -{ - uint32_t s = mbuf->pkt_len; - struct ether_addr *ea; - - stats->bytes += s; - - if (s == 64) { - stats->size_bins[1]++; - } else if (s > 64 && s < 1024) { - uint32_t bin; - - /* count zeros, and offset into correct bin */ - bin = (sizeof(s) * 8) - __builtin_clz(s) - 5; - stats->size_bins[bin]++; - } else { - if (s < 64) - stats->size_bins[0]++; - else if (s < 1519) - stats->size_bins[6]++; - else if (s >= 1519) - stats->size_bins[7]++; - } - - ea = rte_pktmbuf_mtod(mbuf, struct ether_addr *); - if (is_multicast_ether_addr(ea)) { - if (is_broadcast_ether_addr(ea)) - stats->broadcast++; - else - stats->multicast++; - } -} - -static inline void -virtio_rx_stats_updated(struct virtnet_rx *rxvq, struct rte_mbuf *m) -{ - VIRTIO_DUMP_PACKET(m, m->data_len); - - virtio_update_packet_stats(&rxvq->stats, m); -} - /* Optionally fill offload information in structure */ -static int +static inline int virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr) { struct rte_net_hdr_lens hdr_lens; @@ -883,7 +948,6 @@ virtio_rx_offload(struct rte_mbuf *m, struct virtio_net_hdr *hdr) return 0; } -#define VIRTIO_MBUF_BURST_SZ 64 #define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc)) uint16_t virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) @@ -891,7 +955,7 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) struct virtnet_rx *rxvq = rx_queue; struct virtqueue *vq = rxvq->vq; struct virtio_hw *hw = vq->hw; - struct rte_mbuf *rxm, *new_mbuf; + struct rte_mbuf *rxm; uint16_t nb_used, num, nb_rx; uint32_t len[VIRTIO_MBUF_BURST_SZ]; struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; @@ -904,9 +968,7 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) if (unlikely(hw->started == 0)) return nb_rx; - nb_used = VIRTQUEUE_NUSED(vq); - - virtio_rmb(); + nb_used = virtqueue_nused(vq); num = likely(nb_used <= nb_pkts) ? nb_used : nb_pkts; if (unlikely(num > VIRTIO_MBUF_BURST_SZ)) @@ -925,7 +987,7 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) PMD_RX_LOG(DEBUG, "packet len:%d", len[i]); - if (unlikely(len[i] < hdr_size + ETHER_HDR_LEN)) { + if (unlikely(len[i] < hdr_size + RTE_ETHER_HDR_LEN)) { PMD_RX_LOG(ERR, "Packet drop"); nb_enqueued++; virtio_discard_rxbuf(vq, rxm); @@ -961,21 +1023,25 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) rxvq->stats.packets += nb_rx; /* Allocate new mbuf for the used descriptor */ - while (likely(!virtqueue_full(vq))) { - new_mbuf = rte_mbuf_raw_alloc(rxvq->mpool); - if (unlikely(new_mbuf == NULL)) { - struct rte_eth_dev *dev - = &rte_eth_devices[rxvq->port_id]; - dev->data->rx_mbuf_alloc_failed++; - break; - } - error = virtqueue_enqueue_recv_refill(vq, new_mbuf); - if (unlikely(error)) { - rte_pktmbuf_free(new_mbuf); - break; - } - nb_enqueued++; - } + if (likely(!virtqueue_full(vq))) { + uint16_t free_cnt = vq->vq_free_cnt; + struct rte_mbuf *new_pkts[free_cnt]; + + if (likely(rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts, + free_cnt) == 0)) { + error = virtqueue_enqueue_recv_refill(vq, new_pkts, + free_cnt); + if (unlikely(error)) { + for (i = 0; i < free_cnt; i++) + rte_pktmbuf_free(new_pkts[i]); + } + nb_enqueued += free_cnt; + } else { + struct rte_eth_dev *dev = + &rte_eth_devices[rxvq->port_id]; + dev->data->rx_mbuf_alloc_failed += free_cnt; + } + } if (likely(nb_enqueued)) { vq_update_avail_idx(vq); @@ -990,7 +1056,109 @@ virtio_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) } uint16_t -virtio_recv_mergeable_pkts_inorder(void *rx_queue, +virtio_recv_pkts_packed(void *rx_queue, struct rte_mbuf **rx_pkts, + uint16_t nb_pkts) +{ + struct virtnet_rx *rxvq = rx_queue; + struct virtqueue *vq = rxvq->vq; + struct virtio_hw *hw = vq->hw; + struct rte_mbuf *rxm; + uint16_t num, nb_rx; + uint32_t len[VIRTIO_MBUF_BURST_SZ]; + struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; + int error; + uint32_t i, nb_enqueued; + uint32_t hdr_size; + struct virtio_net_hdr *hdr; + + nb_rx = 0; + if (unlikely(hw->started == 0)) + return nb_rx; + + num = RTE_MIN(VIRTIO_MBUF_BURST_SZ, nb_pkts); + if (likely(num > DESC_PER_CACHELINE)) + num = num - ((vq->vq_used_cons_idx + num) % DESC_PER_CACHELINE); + + num = virtqueue_dequeue_burst_rx_packed(vq, rcv_pkts, len, num); + PMD_RX_LOG(DEBUG, "dequeue:%d", num); + + nb_enqueued = 0; + hdr_size = hw->vtnet_hdr_size; + + for (i = 0; i < num; i++) { + rxm = rcv_pkts[i]; + + PMD_RX_LOG(DEBUG, "packet len:%d", len[i]); + + if (unlikely(len[i] < hdr_size + RTE_ETHER_HDR_LEN)) { + PMD_RX_LOG(ERR, "Packet drop"); + nb_enqueued++; + virtio_discard_rxbuf(vq, rxm); + rxvq->stats.errors++; + continue; + } + + rxm->port = rxvq->port_id; + rxm->data_off = RTE_PKTMBUF_HEADROOM; + rxm->ol_flags = 0; + rxm->vlan_tci = 0; + + rxm->pkt_len = (uint32_t)(len[i] - hdr_size); + rxm->data_len = (uint16_t)(len[i] - hdr_size); + + hdr = (struct virtio_net_hdr *)((char *)rxm->buf_addr + + RTE_PKTMBUF_HEADROOM - hdr_size); + + if (hw->vlan_strip) + rte_vlan_strip(rxm); + + if (hw->has_rx_offload && virtio_rx_offload(rxm, hdr) < 0) { + virtio_discard_rxbuf(vq, rxm); + rxvq->stats.errors++; + continue; + } + + virtio_rx_stats_updated(rxvq, rxm); + + rx_pkts[nb_rx++] = rxm; + } + + rxvq->stats.packets += nb_rx; + + /* Allocate new mbuf for the used descriptor */ + if (likely(!virtqueue_full(vq))) { + uint16_t free_cnt = vq->vq_free_cnt; + struct rte_mbuf *new_pkts[free_cnt]; + + if (likely(rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts, + free_cnt) == 0)) { + error = virtqueue_enqueue_recv_refill_packed(vq, + new_pkts, free_cnt); + if (unlikely(error)) { + for (i = 0; i < free_cnt; i++) + rte_pktmbuf_free(new_pkts[i]); + } + nb_enqueued += free_cnt; + } else { + struct rte_eth_dev *dev = + &rte_eth_devices[rxvq->port_id]; + dev->data->rx_mbuf_alloc_failed += free_cnt; + } + } + + if (likely(nb_enqueued)) { + if (unlikely(virtqueue_kick_prepare_packed(vq))) { + virtqueue_notify(vq); + PMD_RX_LOG(DEBUG, "Notified"); + } + } + + return nb_rx; +} + + +uint16_t +virtio_recv_pkts_inorder(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts) { @@ -998,7 +1166,7 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, struct virtqueue *vq = rxvq->vq; struct virtio_hw *hw = vq->hw; struct rte_mbuf *rxm; - struct rte_mbuf *prev; + struct rte_mbuf *prev = NULL; uint16_t nb_used, num, nb_rx; uint32_t len[VIRTIO_MBUF_BURST_SZ]; struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; @@ -1013,12 +1181,10 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, if (unlikely(hw->started == 0)) return nb_rx; - nb_used = VIRTQUEUE_NUSED(vq); + nb_used = virtqueue_nused(vq); nb_used = RTE_MIN(nb_used, nb_pkts); nb_used = RTE_MIN(nb_used, VIRTIO_MBUF_BURST_SZ); - virtio_rmb(); - PMD_RX_LOG(DEBUG, "used:%d", nb_used); nb_enqueued = 0; @@ -1036,7 +1202,7 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, rxm = rcv_pkts[i]; - if (unlikely(len[i] < hdr_size + ETHER_HDR_LEN)) { + if (unlikely(len[i] < hdr_size + RTE_ETHER_HDR_LEN)) { PMD_RX_LOG(ERR, "Packet drop"); nb_enqueued++; virtio_discard_rxbuf_inorder(vq, rxm); @@ -1047,10 +1213,14 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, header = (struct virtio_net_hdr_mrg_rxbuf *) ((char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM - hdr_size); - seg_num = header->num_buffers; - if (seg_num == 0) + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + seg_num = header->num_buffers; + if (seg_num == 0) + seg_num = 1; + } else { seg_num = 1; + } rxm->data_off = RTE_PKTMBUF_HEADROOM; rxm->nb_segs = seg_num; @@ -1086,11 +1256,8 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, rxm->data_len = (uint16_t)(len[i]); rx_pkts[nb_rx]->pkt_len += (uint32_t)(len[i]); - rx_pkts[nb_rx]->data_len += (uint16_t)(len[i]); - - if (prev) - prev->next = rxm; + prev->next = rxm; prev = rxm; seg_res -= 1; } @@ -1106,8 +1273,7 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, uint16_t rcv_cnt = RTE_MIN((uint16_t)seg_res, VIRTIO_MBUF_BURST_SZ); - prev = rcv_pkts[nb_rx]; - if (likely(VIRTQUEUE_NUSED(vq) >= rcv_cnt)) { + if (likely(virtqueue_nused(vq) >= rcv_cnt)) { num = virtqueue_dequeue_rx_inorder(vq, rcv_pkts, len, rcv_cnt); uint16_t extra_idx = 0; @@ -1122,7 +1288,6 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, prev->next = rxm; prev = rxm; rx_pkts[nb_rx]->pkt_len += len[extra_idx]; - rx_pkts[nb_rx]->data_len += len[extra_idx]; extra_idx += 1; }; seg_res -= rcv_cnt; @@ -1134,7 +1299,7 @@ virtio_recv_mergeable_pkts_inorder(void *rx_queue, } else { PMD_RX_LOG(ERR, "No enough segments for packet."); - virtio_discard_rxbuf_inorder(vq, prev); + rte_pktmbuf_free(rx_pkts[nb_rx]); rxvq->stats.errors++; break; } @@ -1184,53 +1349,44 @@ virtio_recv_mergeable_pkts(void *rx_queue, struct virtnet_rx *rxvq = rx_queue; struct virtqueue *vq = rxvq->vq; struct virtio_hw *hw = vq->hw; - struct rte_mbuf *rxm, *new_mbuf; - uint16_t nb_used, num, nb_rx; + struct rte_mbuf *rxm; + struct rte_mbuf *prev = NULL; + uint16_t nb_used, num, nb_rx = 0; uint32_t len[VIRTIO_MBUF_BURST_SZ]; struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; - struct rte_mbuf *prev; int error; - uint32_t i, nb_enqueued; - uint32_t seg_num; - uint16_t extra_idx; - uint32_t seg_res; - uint32_t hdr_size; + uint32_t nb_enqueued = 0; + uint32_t seg_num = 0; + uint32_t seg_res = 0; + uint32_t hdr_size = hw->vtnet_hdr_size; + int32_t i; - nb_rx = 0; if (unlikely(hw->started == 0)) return nb_rx; - nb_used = VIRTQUEUE_NUSED(vq); - - virtio_rmb(); + nb_used = virtqueue_nused(vq); PMD_RX_LOG(DEBUG, "used:%d", nb_used); - i = 0; - nb_enqueued = 0; - seg_num = 0; - extra_idx = 0; - seg_res = 0; - hdr_size = hw->vtnet_hdr_size; - - while (i < nb_used) { - struct virtio_net_hdr_mrg_rxbuf *header; + num = likely(nb_used <= nb_pkts) ? nb_used : nb_pkts; + if (unlikely(num > VIRTIO_MBUF_BURST_SZ)) + num = VIRTIO_MBUF_BURST_SZ; + if (likely(num > DESC_PER_CACHELINE)) + num = num - ((vq->vq_used_cons_idx + num) % + DESC_PER_CACHELINE); - if (nb_rx == nb_pkts) - break; - num = virtqueue_dequeue_burst_rx(vq, rcv_pkts, len, 1); - if (num != 1) - continue; + num = virtqueue_dequeue_burst_rx(vq, rcv_pkts, len, num); - i++; + for (i = 0; i < num; i++) { + struct virtio_net_hdr_mrg_rxbuf *header; PMD_RX_LOG(DEBUG, "dequeue:%d", num); - PMD_RX_LOG(DEBUG, "packet len:%d", len[0]); + PMD_RX_LOG(DEBUG, "packet len:%d", len[i]); - rxm = rcv_pkts[0]; + rxm = rcv_pkts[i]; - if (unlikely(len[0] < hdr_size + ETHER_HDR_LEN)) { + if (unlikely(len[i] < hdr_size + RTE_ETHER_HDR_LEN)) { PMD_RX_LOG(ERR, "Packet drop"); nb_enqueued++; virtio_discard_rxbuf(vq, rxm); @@ -1238,10 +1394,10 @@ virtio_recv_mergeable_pkts(void *rx_queue, continue; } - header = (struct virtio_net_hdr_mrg_rxbuf *)((char *)rxm->buf_addr + - RTE_PKTMBUF_HEADROOM - hdr_size); + header = (struct virtio_net_hdr_mrg_rxbuf *) + ((char *)rxm->buf_addr + RTE_PKTMBUF_HEADROOM + - hdr_size); seg_num = header->num_buffers; - if (seg_num == 0) seg_num = 1; @@ -1249,10 +1405,11 @@ virtio_recv_mergeable_pkts(void *rx_queue, rxm->nb_segs = seg_num; rxm->ol_flags = 0; rxm->vlan_tci = 0; - rxm->pkt_len = (uint32_t)(len[0] - hdr_size); - rxm->data_len = (uint16_t)(len[0] - hdr_size); + rxm->pkt_len = (uint32_t)(len[i] - hdr_size); + rxm->data_len = (uint16_t)(len[i] - hdr_size); rxm->port = rxvq->port_id; + rx_pkts[nb_rx] = rxm; prev = rxm; @@ -1263,87 +1420,393 @@ virtio_recv_mergeable_pkts(void *rx_queue, continue; } + if (hw->vlan_strip) + rte_vlan_strip(rx_pkts[nb_rx]); + seg_res = seg_num - 1; - while (seg_res != 0) { - /* - * Get extra segments for current uncompleted packet. - */ - uint16_t rcv_cnt = - RTE_MIN(seg_res, RTE_DIM(rcv_pkts)); - if (likely(VIRTQUEUE_NUSED(vq) >= rcv_cnt)) { - uint32_t rx_num = - virtqueue_dequeue_burst_rx(vq, - rcv_pkts, len, rcv_cnt); - i += rx_num; - rcv_cnt = rx_num; - } else { - PMD_RX_LOG(ERR, - "No enough segments for packet."); - nb_enqueued++; - virtio_discard_rxbuf(vq, rxm); - rxvq->stats.errors++; - break; - } + /* Merge remaining segments */ + while (seg_res != 0 && i < (num - 1)) { + i++; - extra_idx = 0; + rxm = rcv_pkts[i]; + rxm->data_off = RTE_PKTMBUF_HEADROOM - hdr_size; + rxm->pkt_len = (uint32_t)(len[i]); + rxm->data_len = (uint16_t)(len[i]); + + rx_pkts[nb_rx]->pkt_len += (uint32_t)(len[i]); + + prev->next = rxm; + prev = rxm; + seg_res -= 1; + } + + if (!seg_res) { + virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]); + nb_rx++; + } + } + /* Last packet still need merge segments */ + while (seg_res != 0) { + uint16_t rcv_cnt = RTE_MIN((uint16_t)seg_res, + VIRTIO_MBUF_BURST_SZ); + + if (likely(virtqueue_nused(vq) >= rcv_cnt)) { + num = virtqueue_dequeue_burst_rx(vq, rcv_pkts, len, + rcv_cnt); + uint16_t extra_idx = 0; + + rcv_cnt = num; while (extra_idx < rcv_cnt) { rxm = rcv_pkts[extra_idx]; - - rxm->data_off = RTE_PKTMBUF_HEADROOM - hdr_size; + rxm->data_off = + RTE_PKTMBUF_HEADROOM - hdr_size; rxm->pkt_len = (uint32_t)(len[extra_idx]); rxm->data_len = (uint16_t)(len[extra_idx]); - - if (prev) - prev->next = rxm; - + prev->next = rxm; prev = rxm; - rx_pkts[nb_rx]->pkt_len += rxm->pkt_len; - extra_idx++; + rx_pkts[nb_rx]->pkt_len += len[extra_idx]; + extra_idx += 1; }; seg_res -= rcv_cnt; + + if (!seg_res) { + virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]); + nb_rx++; + } + } else { + PMD_RX_LOG(ERR, + "No enough segments for packet."); + rte_pktmbuf_free(rx_pkts[nb_rx]); + rxvq->stats.errors++; + break; + } + } + + rxvq->stats.packets += nb_rx; + + /* Allocate new mbuf for the used descriptor */ + if (likely(!virtqueue_full(vq))) { + /* free_cnt may include mrg descs */ + uint16_t free_cnt = vq->vq_free_cnt; + struct rte_mbuf *new_pkts[free_cnt]; + + if (!rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts, free_cnt)) { + error = virtqueue_enqueue_recv_refill(vq, new_pkts, + free_cnt); + if (unlikely(error)) { + for (i = 0; i < free_cnt; i++) + rte_pktmbuf_free(new_pkts[i]); + } + nb_enqueued += free_cnt; + } else { + struct rte_eth_dev *dev = + &rte_eth_devices[rxvq->port_id]; + dev->data->rx_mbuf_alloc_failed += free_cnt; + } + } + + if (likely(nb_enqueued)) { + vq_update_avail_idx(vq); + + if (unlikely(virtqueue_kick_prepare(vq))) { + virtqueue_notify(vq); + PMD_RX_LOG(DEBUG, "Notified"); + } + } + + return nb_rx; +} + +uint16_t +virtio_recv_mergeable_pkts_packed(void *rx_queue, + struct rte_mbuf **rx_pkts, + uint16_t nb_pkts) +{ + struct virtnet_rx *rxvq = rx_queue; + struct virtqueue *vq = rxvq->vq; + struct virtio_hw *hw = vq->hw; + struct rte_mbuf *rxm; + struct rte_mbuf *prev = NULL; + uint16_t num, nb_rx = 0; + uint32_t len[VIRTIO_MBUF_BURST_SZ]; + struct rte_mbuf *rcv_pkts[VIRTIO_MBUF_BURST_SZ]; + uint32_t nb_enqueued = 0; + uint32_t seg_num = 0; + uint32_t seg_res = 0; + uint32_t hdr_size = hw->vtnet_hdr_size; + int32_t i; + int error; + + if (unlikely(hw->started == 0)) + return nb_rx; + + + num = nb_pkts; + if (unlikely(num > VIRTIO_MBUF_BURST_SZ)) + num = VIRTIO_MBUF_BURST_SZ; + if (likely(num > DESC_PER_CACHELINE)) + num = num - ((vq->vq_used_cons_idx + num) % DESC_PER_CACHELINE); + + num = virtqueue_dequeue_burst_rx_packed(vq, rcv_pkts, len, num); + + for (i = 0; i < num; i++) { + struct virtio_net_hdr_mrg_rxbuf *header; + + PMD_RX_LOG(DEBUG, "dequeue:%d", num); + PMD_RX_LOG(DEBUG, "packet len:%d", len[i]); + + rxm = rcv_pkts[i]; + + if (unlikely(len[i] < hdr_size + RTE_ETHER_HDR_LEN)) { + PMD_RX_LOG(ERR, "Packet drop"); + nb_enqueued++; + virtio_discard_rxbuf(vq, rxm); + rxvq->stats.errors++; + continue; + } + + header = (struct virtio_net_hdr_mrg_rxbuf *)((char *) + rxm->buf_addr + RTE_PKTMBUF_HEADROOM - hdr_size); + seg_num = header->num_buffers; + + if (seg_num == 0) + seg_num = 1; + + rxm->data_off = RTE_PKTMBUF_HEADROOM; + rxm->nb_segs = seg_num; + rxm->ol_flags = 0; + rxm->vlan_tci = 0; + rxm->pkt_len = (uint32_t)(len[i] - hdr_size); + rxm->data_len = (uint16_t)(len[i] - hdr_size); + + rxm->port = rxvq->port_id; + rx_pkts[nb_rx] = rxm; + prev = rxm; + + if (hw->has_rx_offload && + virtio_rx_offload(rxm, &header->hdr) < 0) { + virtio_discard_rxbuf(vq, rxm); + rxvq->stats.errors++; + continue; } if (hw->vlan_strip) rte_vlan_strip(rx_pkts[nb_rx]); - VIRTIO_DUMP_PACKET(rx_pkts[nb_rx], - rx_pkts[nb_rx]->data_len); + seg_res = seg_num - 1; + + /* Merge remaining segments */ + while (seg_res != 0 && i < (num - 1)) { + i++; - virtio_update_packet_stats(&rxvq->stats, rx_pkts[nb_rx]); - nb_rx++; + rxm = rcv_pkts[i]; + rxm->data_off = RTE_PKTMBUF_HEADROOM - hdr_size; + rxm->pkt_len = (uint32_t)(len[i]); + rxm->data_len = (uint16_t)(len[i]); + + rx_pkts[nb_rx]->pkt_len += (uint32_t)(len[i]); + + prev->next = rxm; + prev = rxm; + seg_res -= 1; + } + + if (!seg_res) { + virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]); + nb_rx++; + } + } + + /* Last packet still need merge segments */ + while (seg_res != 0) { + uint16_t rcv_cnt = RTE_MIN((uint16_t)seg_res, + VIRTIO_MBUF_BURST_SZ); + uint16_t extra_idx = 0; + + rcv_cnt = virtqueue_dequeue_burst_rx_packed(vq, rcv_pkts, + len, rcv_cnt); + if (unlikely(rcv_cnt == 0)) { + PMD_RX_LOG(ERR, "No enough segments for packet."); + rte_pktmbuf_free(rx_pkts[nb_rx]); + rxvq->stats.errors++; + break; + } + + while (extra_idx < rcv_cnt) { + rxm = rcv_pkts[extra_idx]; + + rxm->data_off = RTE_PKTMBUF_HEADROOM - hdr_size; + rxm->pkt_len = (uint32_t)(len[extra_idx]); + rxm->data_len = (uint16_t)(len[extra_idx]); + + prev->next = rxm; + prev = rxm; + rx_pkts[nb_rx]->pkt_len += len[extra_idx]; + extra_idx += 1; + } + seg_res -= rcv_cnt; + if (!seg_res) { + virtio_rx_stats_updated(rxvq, rx_pkts[nb_rx]); + nb_rx++; + } } rxvq->stats.packets += nb_rx; /* Allocate new mbuf for the used descriptor */ - while (likely(!virtqueue_full(vq))) { - new_mbuf = rte_mbuf_raw_alloc(rxvq->mpool); - if (unlikely(new_mbuf == NULL)) { - struct rte_eth_dev *dev - = &rte_eth_devices[rxvq->port_id]; - dev->data->rx_mbuf_alloc_failed++; + if (likely(!virtqueue_full(vq))) { + /* free_cnt may include mrg descs */ + uint16_t free_cnt = vq->vq_free_cnt; + struct rte_mbuf *new_pkts[free_cnt]; + + if (!rte_pktmbuf_alloc_bulk(rxvq->mpool, new_pkts, free_cnt)) { + error = virtqueue_enqueue_recv_refill_packed(vq, + new_pkts, free_cnt); + if (unlikely(error)) { + for (i = 0; i < free_cnt; i++) + rte_pktmbuf_free(new_pkts[i]); + } + nb_enqueued += free_cnt; + } else { + struct rte_eth_dev *dev = + &rte_eth_devices[rxvq->port_id]; + dev->data->rx_mbuf_alloc_failed += free_cnt; + } + } + + if (likely(nb_enqueued)) { + if (unlikely(virtqueue_kick_prepare_packed(vq))) { + virtqueue_notify(vq); + PMD_RX_LOG(DEBUG, "Notified"); + } + } + + return nb_rx; +} + +uint16_t +virtio_xmit_pkts_prepare(void *tx_queue __rte_unused, struct rte_mbuf **tx_pkts, + uint16_t nb_pkts) +{ + uint16_t nb_tx; + int error; + + for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) { + struct rte_mbuf *m = tx_pkts[nb_tx]; + +#ifdef RTE_LIBRTE_ETHDEV_DEBUG + error = rte_validate_tx_offload(m); + if (unlikely(error)) { + rte_errno = -error; break; } - error = virtqueue_enqueue_recv_refill(vq, new_mbuf); +#endif + + /* Do VLAN tag insertion */ + if (unlikely(m->ol_flags & PKT_TX_VLAN_PKT)) { + error = rte_vlan_insert(&m); + /* rte_vlan_insert() may change pointer + * even in the case of failure + */ + tx_pkts[nb_tx] = m; + + if (unlikely(error)) { + rte_errno = -error; + break; + } + } + + error = rte_net_intel_cksum_prepare(m); if (unlikely(error)) { - rte_pktmbuf_free(new_mbuf); + rte_errno = -error; break; } - nb_enqueued++; + + if (m->ol_flags & PKT_TX_TCP_SEG) + virtio_tso_fix_cksum(m); } - if (likely(nb_enqueued)) { - vq_update_avail_idx(vq); + return nb_tx; +} - if (unlikely(virtqueue_kick_prepare(vq))) { +uint16_t +virtio_xmit_pkts_packed(void *tx_queue, struct rte_mbuf **tx_pkts, + uint16_t nb_pkts) +{ + struct virtnet_tx *txvq = tx_queue; + struct virtqueue *vq = txvq->vq; + struct virtio_hw *hw = vq->hw; + uint16_t hdr_size = hw->vtnet_hdr_size; + uint16_t nb_tx = 0; + bool in_order = vtpci_with_feature(hw, VIRTIO_F_IN_ORDER); + + if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts)) + return nb_tx; + + if (unlikely(nb_pkts < 1)) + return nb_pkts; + + PMD_TX_LOG(DEBUG, "%d packets to xmit", nb_pkts); + + if (nb_pkts > vq->vq_free_cnt) + virtio_xmit_cleanup_packed(vq, nb_pkts - vq->vq_free_cnt, + in_order); + + for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) { + struct rte_mbuf *txm = tx_pkts[nb_tx]; + int can_push = 0, slots, need; + + /* optimize ring usage */ + if ((vtpci_with_feature(hw, VIRTIO_F_ANY_LAYOUT) || + vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) && + rte_mbuf_refcnt_read(txm) == 1 && + RTE_MBUF_DIRECT(txm) && + txm->nb_segs == 1 && + rte_pktmbuf_headroom(txm) >= hdr_size && + rte_is_aligned(rte_pktmbuf_mtod(txm, char *), + __alignof__(struct virtio_net_hdr_mrg_rxbuf))) + can_push = 1; + + /* How many main ring entries are needed to this Tx? + * any_layout => number of segments + * default => number of segments + 1 + */ + slots = txm->nb_segs + !can_push; + need = slots - vq->vq_free_cnt; + + /* Positive value indicates it need free vring descriptors */ + if (unlikely(need > 0)) { + virtio_xmit_cleanup_packed(vq, need, in_order); + need = slots - vq->vq_free_cnt; + if (unlikely(need > 0)) { + PMD_TX_LOG(ERR, + "No free tx descriptors to transmit"); + break; + } + } + + /* Enqueue Packet buffers */ + if (can_push) + virtqueue_enqueue_xmit_packed_fast(txvq, txm, in_order); + else + virtqueue_enqueue_xmit_packed(txvq, txm, slots, 0, + in_order); + + virtio_update_packet_stats(&txvq->stats, txm); + } + + txvq->stats.packets += nb_tx; + + if (likely(nb_tx)) { + if (unlikely(virtqueue_kick_prepare_packed(vq))) { virtqueue_notify(vq); - PMD_RX_LOG(DEBUG, "Notified"); + PMD_TX_LOG(DEBUG, "Notified backend after xmit"); } } - return nb_rx; + return nb_tx; } uint16_t @@ -1354,7 +1817,6 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) struct virtio_hw *hw = vq->hw; uint16_t hdr_size = hw->vtnet_hdr_size; uint16_t nb_used, nb_tx = 0; - int error; if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts)) return nb_tx; @@ -1363,9 +1825,9 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) return nb_pkts; PMD_TX_LOG(DEBUG, "%d packets to xmit", nb_pkts); - nb_used = VIRTQUEUE_NUSED(vq); - virtio_rmb(); + nb_used = virtqueue_nused(vq); + if (likely(nb_used > vq->vq_nentries - vq->vq_free_thresh)) virtio_xmit_cleanup(vq, nb_used); @@ -1373,15 +1835,6 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) struct rte_mbuf *txm = tx_pkts[nb_tx]; int can_push = 0, use_indirect = 0, slots, need; - /* Do VLAN tag insertion */ - if (unlikely(txm->ol_flags & PKT_TX_VLAN_PKT)) { - error = rte_vlan_insert(&txm); - if (unlikely(error)) { - rte_pktmbuf_free(txm); - continue; - } - } - /* optimize ring usage */ if ((vtpci_with_feature(hw, VIRTIO_F_ANY_LAYOUT) || vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) && @@ -1406,8 +1859,8 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) /* Positive value indicates it need free vring descriptors */ if (unlikely(need > 0)) { - nb_used = VIRTQUEUE_NUSED(vq); - virtio_rmb(); + nb_used = virtqueue_nused(vq); + need = RTE_MIN(need, (int)nb_used); virtio_xmit_cleanup(vq, need); @@ -1440,6 +1893,20 @@ virtio_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts) return nb_tx; } +static __rte_always_inline int +virtio_xmit_try_cleanup_inorder(struct virtqueue *vq, uint16_t need) +{ + uint16_t nb_used, nb_clean, nb_descs; + + nb_descs = vq->vq_free_cnt + need; + nb_used = virtqueue_nused(vq); + nb_clean = RTE_MIN(need, (int)nb_used); + + virtio_xmit_cleanup_inorder(vq, nb_clean); + + return nb_descs - vq->vq_free_cnt; +} + uint16_t virtio_xmit_pkts_inorder(void *tx_queue, struct rte_mbuf **tx_pkts, @@ -1449,9 +1916,9 @@ virtio_xmit_pkts_inorder(void *tx_queue, struct virtqueue *vq = txvq->vq; struct virtio_hw *hw = vq->hw; uint16_t hdr_size = hw->vtnet_hdr_size; - uint16_t nb_used, nb_avail, nb_tx = 0, nb_inorder_pkts = 0; + uint16_t nb_used, nb_tx = 0, nb_inorder_pkts = 0; struct rte_mbuf *inorder_pkts[nb_pkts]; - int error; + int need; if (unlikely(hw->started == 0 && tx_pkts != hw->inject_pkts)) return nb_tx; @@ -1461,29 +1928,14 @@ virtio_xmit_pkts_inorder(void *tx_queue, VIRTQUEUE_DUMP(vq); PMD_TX_LOG(DEBUG, "%d packets to xmit", nb_pkts); - nb_used = VIRTQUEUE_NUSED(vq); + nb_used = virtqueue_nused(vq); - virtio_rmb(); if (likely(nb_used > vq->vq_nentries - vq->vq_free_thresh)) virtio_xmit_cleanup_inorder(vq, nb_used); - if (unlikely(!vq->vq_free_cnt)) - virtio_xmit_cleanup_inorder(vq, nb_used); - - nb_avail = RTE_MIN(vq->vq_free_cnt, nb_pkts); - - for (nb_tx = 0; nb_tx < nb_avail; nb_tx++) { + for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) { struct rte_mbuf *txm = tx_pkts[nb_tx]; - int slots, need; - - /* Do VLAN tag insertion */ - if (unlikely(txm->ol_flags & PKT_TX_VLAN_PKT)) { - error = rte_vlan_insert(&txm); - if (unlikely(error)) { - rte_pktmbuf_free(txm); - continue; - } - } + int slots; /* optimize ring usage */ if ((vtpci_with_feature(hw, VIRTIO_F_ANY_LAYOUT) || @@ -1497,11 +1949,21 @@ virtio_xmit_pkts_inorder(void *tx_queue, inorder_pkts[nb_inorder_pkts] = txm; nb_inorder_pkts++; - virtio_update_packet_stats(&txvq->stats, txm); continue; } if (nb_inorder_pkts) { + need = nb_inorder_pkts - vq->vq_free_cnt; + if (unlikely(need > 0)) { + need = virtio_xmit_try_cleanup_inorder(vq, + need); + if (unlikely(need > 0)) { + PMD_TX_LOG(ERR, + "No free tx descriptors to " + "transmit"); + break; + } + } virtqueue_enqueue_xmit_inorder(txvq, inorder_pkts, nb_inorder_pkts); nb_inorder_pkts = 0; @@ -1510,13 +1972,7 @@ virtio_xmit_pkts_inorder(void *tx_queue, slots = txm->nb_segs + 1; need = slots - vq->vq_free_cnt; if (unlikely(need > 0)) { - nb_used = VIRTQUEUE_NUSED(vq); - virtio_rmb(); - need = RTE_MIN(need, (int)nb_used); - - virtio_xmit_cleanup_inorder(vq, need); - - need = slots - vq->vq_free_cnt; + need = virtio_xmit_try_cleanup_inorder(vq, slots); if (unlikely(need > 0)) { PMD_TX_LOG(ERR, @@ -1531,9 +1987,22 @@ virtio_xmit_pkts_inorder(void *tx_queue, } /* Transmit all inorder packets */ - if (nb_inorder_pkts) + if (nb_inorder_pkts) { + need = nb_inorder_pkts - vq->vq_free_cnt; + if (unlikely(need > 0)) { + need = virtio_xmit_try_cleanup_inorder(vq, + need); + if (unlikely(need > 0)) { + PMD_TX_LOG(ERR, + "No free tx descriptors to transmit"); + nb_inorder_pkts = vq->vq_free_cnt; + nb_tx -= need; + } + } + virtqueue_enqueue_xmit_inorder(txvq, inorder_pkts, nb_inorder_pkts); + } txvq->stats.packets += nb_tx; @@ -1550,3 +2019,21 @@ virtio_xmit_pkts_inorder(void *tx_queue, return nb_tx; } + +#ifndef CC_AVX512_SUPPORT +uint16_t +virtio_recv_pkts_packed_vec(void *rx_queue __rte_unused, + struct rte_mbuf **rx_pkts __rte_unused, + uint16_t nb_pkts __rte_unused) +{ + return 0; +} + +uint16_t +virtio_xmit_pkts_packed_vec(void *tx_queue __rte_unused, + struct rte_mbuf **tx_pkts __rte_unused, + uint16_t nb_pkts __rte_unused) +{ + return 0; +} +#endif /* ifndef CC_AVX512_SUPPORT */