X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_vhost%2Fvirtio_net.c;h=741267345274573d7a15553ef17117f3d5cbdb65;hb=915cf9404225;hp=59ff6c875b1c94d3e13b84b949c78d3e64fab4b0;hpb=25bf7a0b093601013016c2787ff5b21bb5ac6fe8;p=dpdk.git diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c index 59ff6c875b..7412673452 100644 --- a/lib/librte_vhost/virtio_net.c +++ b/lib/librte_vhost/virtio_net.c @@ -1,34 +1,5 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2016 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation */ #include @@ -44,19 +15,68 @@ #include #include #include +#include +#include +#include "iotlb.h" #include "vhost.h" #define MAX_PKT_BURST 32 #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 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 __rte_always_inline struct vring_desc * +alloc_copy_ind_table(struct virtio_net *dev, struct vhost_virtqueue *vq, + struct vring_desc *desc) +{ + struct vring_desc *idesc; + uint64_t src, dst; + uint64_t len, remain = desc->len; + uint64_t desc_addr = desc->addr; + + idesc = rte_malloc(__func__, desc->len, 0); + if (unlikely(!idesc)) + return 0; + + dst = (uint64_t)(uintptr_t)idesc; + + while (remain) { + len = remain; + src = vhost_iova_to_vva(dev, vq, desc_addr, &len, + VHOST_ACCESS_RO); + if (unlikely(!src || !len)) { + rte_free(idesc); + return 0; + } + + rte_memcpy((void *)(uintptr_t)dst, (void *)(uintptr_t)src, len); + + remain -= len; + dst += len; + desc_addr += len; + } + + return idesc; +} + +static __rte_always_inline void +free_ind_table(struct vring_desc *idesc) +{ + rte_free(idesc); +} + 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) @@ -64,7 +84,7 @@ do_flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq, rte_memcpy(&vq->used->ring[to], &vq->shadow_used_ring[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)); } @@ -92,6 +112,8 @@ flush_shadow_used_ring(struct virtio_net *dev, struct vhost_virtqueue *vq) rte_smp_wmb(); + vhost_log_cache_sync(dev, vq); + *(volatile uint16_t *)&vq->used->idx += vq->shadow_used_idx; vhost_log_used_vring(dev, vq, offsetof(struct vring_used, idx), sizeof(vq->used->idx)); @@ -116,7 +138,7 @@ do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq) 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); + vhost_log_cache_write(dev, vq, elem[i].log_addr, elem[i].len); PRINT_PACKET(dev, (uintptr_t)elem[i].dst, elem[i].len, 0); } } @@ -138,7 +160,7 @@ do_data_copy_dequeue(struct vhost_virtqueue *vq) (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; @@ -187,6 +209,11 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_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); @@ -194,214 +221,6 @@ virtio_enqueue_offload(struct rte_mbuf *m_buf, struct virtio_net_hdr *net_hdr) } } -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) -{ - 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 = rte_vhost_gpa_to_vva(dev->mem, desc->addr); - /* - * 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; - - 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); - } - - /* 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; - } - - desc = &descs[desc->next]; - desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr); - if (unlikely(!desc_addr)) { - error = -1; - goto out; - } - - desc_offset = 0; - desc_avail = desc->len; - } - - 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++; - } - - mbuf_avail -= cpy_len; - mbuf_offset += cpy_len; - desc_avail -= cpy_len; - desc_offset += cpy_len; - } - -out: - vq->batch_copy_nb_elems = copy_nb; - - return error; -} - -/** - * 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) -{ - 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; - } - - vq = dev->virtqueue[queue_id]; - if (unlikely(vq->enabled == 0)) - return 0; - - 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) - return 0; - - LOG_DEBUG(VHOST_DATA, "(%d) start_idx %d | end_idx %d\n", - dev->vid, start_idx, start_idx + count); - - vq->batch_copy_nb_elems = 0; - - /* 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])); - } - - rte_prefetch0(&vq->desc[desc_indexes[0]]); - for (i = 0; i < count; i++) { - uint16_t desc_idx = desc_indexes[i]; - int err; - - if (vq->desc[desc_idx].flags & VRING_DESC_F_INDIRECT) { - descs = (struct vring_desc *)(uintptr_t) - rte_vhost_gpa_to_vva(dev->mem, - vq->desc[desc_idx].addr); - if (unlikely(!descs)) { - count = i; - break; - } - - desc_idx = 0; - sz = vq->desc[desc_idx].len / sizeof(*descs); - } else { - descs = vq->desc; - sz = vq->size; - } - - err = copy_mbuf_to_desc(dev, vq, descs, pkts[i], desc_idx, sz); - if (unlikely(err)) { - count = i; - break; - } - - if (i + 1 < count) - rte_prefetch0(&vq->desc[desc_indexes[i+1]]); - } - - 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)); - - /* flush used->idx update before we read avail->flags. */ - rte_mb(); - - /* Kick the guest if necessary. */ - if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT) - && (vq->callfd >= 0)) - eventfd_write(vq->callfd, (eventfd_t)1); - 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, @@ -411,22 +230,41 @@ fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq, uint16_t idx = vq->avail->ring[avail_idx & (vq->size - 1)]; uint32_t vec_id = *vec_idx; uint32_t len = 0; + uint64_t dlen; struct vring_desc *descs = vq->desc; + struct vring_desc *idesc = NULL; *desc_chain_head = idx; if (vq->desc[idx].flags & VRING_DESC_F_INDIRECT) { + dlen = vq->desc[idx].len; descs = (struct vring_desc *)(uintptr_t) - rte_vhost_gpa_to_vva(dev->mem, vq->desc[idx].addr); + vhost_iova_to_vva(dev, vq, vq->desc[idx].addr, + &dlen, + VHOST_ACCESS_RO); if (unlikely(!descs)) return -1; + if (unlikely(dlen < vq->desc[idx].len)) { + /* + * The indirect desc table is not contiguous + * in process VA space, we have to copy it. + */ + idesc = alloc_copy_ind_table(dev, vq, &vq->desc[idx]); + if (unlikely(!idesc)) + return -1; + + descs = idesc; + } + idx = 0; } while (1) { - if (unlikely(vec_id >= BUF_VECTOR_MAX || idx >= vq->size)) + if (unlikely(vec_id >= BUF_VECTOR_MAX || idx >= vq->size)) { + free_ind_table(idesc); return -1; + } len += descs[idx].len; buf_vec[vec_id].buf_addr = descs[idx].addr; @@ -443,6 +281,9 @@ fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq, *desc_chain_len = len; *vec_idx = vec_id; + if (unlikely(!!idesc)) + free_ind_table(idesc); + return 0; } @@ -450,13 +291,13 @@ fill_vec_buf(struct virtio_net *dev, struct vhost_virtqueue *vq, * 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(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 cur_idx; uint32_t vec_idx = 0; - uint16_t tries = 0; + uint16_t max_tries, tries = 0; uint16_t head_idx = 0; uint16_t len = 0; @@ -464,6 +305,11 @@ reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, *num_buffers = 0; cur_idx = vq->last_avail_idx; + if (rxvq_is_mergeable(dev)) + max_tries = vq->size; + else + max_tries = 1; + while (size > 0) { if (unlikely(cur_idx == avail_head)) return -1; @@ -484,7 +330,7 @@ reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, * can't get enough buf, it means something abnormal * happened. */ - if (unlikely(tries >= vq->size)) + if (unlikely(tries > max_tries)) return -1; } @@ -492,19 +338,20 @@ reserve_avail_buf_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, } 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) { uint32_t vec_idx = 0; - uint64_t desc_addr; + uint64_t desc_addr, desc_gaddr; uint32_t mbuf_offset, mbuf_avail; uint32_t desc_offset, desc_avail; uint32_t cpy_len; + uint64_t desc_chunck_len; uint64_t hdr_addr, hdr_phys_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)) { @@ -512,7 +359,12 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, goto out; } - desc_addr = rte_vhost_gpa_to_vva(dev->mem, buf_vec[vec_idx].buf_addr); + desc_chunck_len = buf_vec[vec_idx].buf_len; + desc_gaddr = buf_vec[vec_idx].buf_addr; + desc_addr = vhost_iova_to_vva(dev, vq, + desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RW); if (buf_vec[vec_idx].buf_len < dev->vhost_hlen || !desc_addr) { error = -1; goto out; @@ -520,14 +372,35 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, hdr_mbuf = m; hdr_addr = desc_addr; - hdr_phys_addr = buf_vec[vec_idx].buf_addr; + if (unlikely(desc_chunck_len < dev->vhost_hlen)) + hdr = &tmp_hdr; + else + hdr = (struct virtio_net_hdr_mrg_rxbuf *)(uintptr_t)hdr_addr; + hdr_phys_addr = desc_gaddr; rte_prefetch0((void *)(uintptr_t)hdr_addr); - LOG_DEBUG(VHOST_DATA, "(%d) RX: num merge buffers %d\n", + VHOST_LOG_DEBUG(VHOST_DATA, "(%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(desc_chunck_len < dev->vhost_hlen)) { + desc_chunck_len = desc_avail; + desc_gaddr += dev->vhost_hlen; + desc_addr = vhost_iova_to_vva(dev, vq, + desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RW); + if (unlikely(!desc_addr)) { + error = -1; + goto out; + } + + desc_offset = 0; + } else { + desc_offset = dev->vhost_hlen; + desc_chunck_len -= dev->vhost_hlen; + } + mbuf_avail = rte_pktmbuf_data_len(m); mbuf_offset = 0; @@ -535,8 +408,13 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, /* done with current desc buf, get the next one */ if (desc_avail == 0) { vec_idx++; - desc_addr = rte_vhost_gpa_to_vva(dev->mem, - buf_vec[vec_idx].buf_addr); + desc_chunck_len = buf_vec[vec_idx].buf_len; + desc_gaddr = buf_vec[vec_idx].buf_addr; + desc_addr = + vhost_iova_to_vva(dev, vq, + desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RW); if (unlikely(!desc_addr)) { error = -1; goto out; @@ -546,6 +424,17 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, rte_prefetch0((void *)(uintptr_t)desc_addr); desc_offset = 0; desc_avail = buf_vec[vec_idx].buf_len; + } else if (unlikely(desc_chunck_len == 0)) { + desc_chunck_len = desc_avail; + desc_gaddr += desc_offset; + desc_addr = vhost_iova_to_vva(dev, vq, + desc_gaddr, + &desc_chunck_len, VHOST_ACCESS_RW); + if (unlikely(!desc_addr)) { + error = -1; + goto out; + } + desc_offset = 0; } /* done with current mbuf, get the next one */ @@ -557,57 +446,87 @@ copy_mbuf_to_desc_mergeable(struct virtio_net *dev, struct vhost_virtqueue *vq, } 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); - - vhost_log_write(dev, hdr_phys_addr, dev->vhost_hlen); - PRINT_PACKET(dev, (uintptr_t)hdr_addr, - dev->vhost_hlen, 0); + if (rxvq_is_mergeable(dev)) + ASSIGN_UNLESS_EQUAL(hdr->num_buffers, + num_buffers); + + if (unlikely(hdr == &tmp_hdr)) { + uint64_t len; + uint64_t remain = dev->vhost_hlen; + uint64_t src = (uint64_t)(uintptr_t)hdr, dst; + uint64_t guest_addr = hdr_phys_addr; + + while (remain) { + len = remain; + dst = vhost_iova_to_vva(dev, vq, + guest_addr, &len, + VHOST_ACCESS_RW); + if (unlikely(!dst || !len)) { + error = -1; + goto out; + } + + rte_memcpy((void *)(uintptr_t)dst, + (void *)(uintptr_t)src, + len); + + PRINT_PACKET(dev, (uintptr_t)dst, + (uint32_t)len, 0); + vhost_log_cache_write(dev, vq, + guest_addr, len); + + remain -= len; + guest_addr += len; + src += len; + } + } else { + PRINT_PACKET(dev, (uintptr_t)hdr_addr, + dev->vhost_hlen, 0); + vhost_log_cache_write(dev, vq, hdr_phys_addr, + dev->vhost_hlen); + } hdr_addr = 0; } - cpy_len = RTE_MIN(desc_avail, mbuf_avail); + cpy_len = RTE_MIN(desc_chunck_len, mbuf_avail); - if (likely(cpy_len > MAX_BATCH_LEN || copy_nb >= vq->size)) { + if (likely(cpy_len > MAX_BATCH_LEN || + vq->batch_copy_nb_elems >= 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, - buf_vec[vec_idx].buf_addr + desc_offset, - cpy_len); + vhost_log_cache_write(dev, vq, desc_gaddr + desc_offset, + cpy_len); PRINT_PACKET(dev, (uintptr_t)(desc_addr + desc_offset), cpy_len, 0); } else { - batch_copy[copy_nb].dst = + batch_copy[vq->batch_copy_nb_elems].dst = (void *)((uintptr_t)(desc_addr + desc_offset)); - batch_copy[copy_nb].src = + 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 = + desc_gaddr + desc_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; + desc_chunck_len -= 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, +virtio_dev_rx(struct virtio_net *dev, uint16_t queue_id, struct rte_mbuf **pkts, uint32_t count) { struct vhost_virtqueue *vq; @@ -616,7 +535,7 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, struct buf_vector buf_vec[BUF_VECTOR_MAX]; uint16_t avail_head; - LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__); + VHOST_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); @@ -624,12 +543,22 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, } vq = dev->virtqueue[queue_id]; + + rte_spinlock_lock(&vq->access_lock); + if (unlikely(vq->enabled == 0)) - return 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) - return 0; + goto out; vq->batch_copy_nb_elems = 0; @@ -640,21 +569,21 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, for (pkt_idx = 0; pkt_idx < count; pkt_idx++) { uint32_t pkt_len = pkts[pkt_idx]->pkt_len + dev->vhost_hlen; - if (unlikely(reserve_avail_buf_mergeable(dev, vq, + if (unlikely(reserve_avail_buf(dev, vq, pkt_len, buf_vec, &num_buffers, avail_head) < 0)) { - LOG_DEBUG(VHOST_DATA, + VHOST_LOG_DEBUG(VHOST_DATA, "(%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_DEBUG(VHOST_DATA, "(%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], + if (copy_mbuf_to_desc(dev, vq, pkts[pkt_idx], buf_vec, num_buffers) < 0) { vq->shadow_used_idx -= num_buffers; break; @@ -667,15 +596,15 @@ virtio_dev_merge_rx(struct virtio_net *dev, uint16_t queue_id, if (likely(vq->shadow_used_idx)) { flush_shadow_used_ring(dev, vq); + vhost_vring_call(dev, vq); + } - /* flush used->idx update before we read avail->flags. */ - rte_mb(); +out: + if (dev->features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)) + vhost_user_iotlb_rd_unlock(vq); - /* Kick the guest if necessary. */ - if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT) - && (vq->callfd >= 0)) - eventfd_write(vq->callfd, (eventfd_t)1); - } +out_access_unlock: + rte_spinlock_unlock(&vq->access_lock); return pkt_idx; } @@ -689,10 +618,14 @@ rte_vhost_enqueue_burst(int vid, uint16_t queue_id, if (!dev) return 0; - 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(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) { + RTE_LOG(ERR, VHOST_DATA, + "(%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 @@ -796,6 +729,11 @@ vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m) 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 udp_hdr); + break; default: RTE_LOG(WARNING, VHOST_DATA, "unsupported gso type %u.\n", hdr->gso_type); @@ -804,45 +742,6 @@ vhost_dequeue_offload(struct virtio_net_hdr *hdr, struct rte_mbuf *m) } } -#define RARP_PKT_SIZE 64 - -static int -make_rarp_packet(struct rte_mbuf *rarp_mbuf, const struct ether_addr *mac) -{ - 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; - } - - /* 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) { @@ -856,16 +755,17 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, struct rte_mempool *mbuf_pool) { struct vring_desc *desc; - uint64_t desc_addr; + uint64_t desc_addr, desc_gaddr; uint32_t desc_avail, desc_offset; uint32_t mbuf_avail, mbuf_offset; uint32_t cpy_len; + uint64_t desc_chunck_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; 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]; @@ -875,15 +775,52 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, goto out; } - desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr); + desc_chunck_len = desc->len; + desc_gaddr = desc->addr; + desc_addr = vhost_iova_to_vva(dev, + vq, desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RO); if (unlikely(!desc_addr)) { 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(desc_chunck_len < sizeof(struct virtio_net_hdr))) { + uint64_t len = desc_chunck_len; + uint64_t remain = sizeof(struct virtio_net_hdr); + uint64_t src = desc_addr; + uint64_t dst = (uint64_t)(uintptr_t)&tmp_hdr; + uint64_t guest_addr = desc_gaddr; + + /* + * No luck, the virtio-net header doesn't fit + * in a contiguous virtual area. + */ + while (remain) { + len = remain; + src = vhost_iova_to_vva(dev, vq, + guest_addr, &len, + VHOST_ACCESS_RO); + if (unlikely(!src || !len)) { + error = -1; + goto out; + } + + rte_memcpy((void *)(uintptr_t)dst, + (void *)(uintptr_t)src, len); + + guest_addr += len; + remain -= len; + dst += len; + } + + hdr = &tmp_hdr; + } else { + hdr = (struct virtio_net_hdr *)((uintptr_t)desc_addr); + rte_prefetch0(hdr); + } } /* @@ -899,7 +836,12 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, goto out; } - desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr); + desc_chunck_len = desc->len; + desc_gaddr = desc->addr; + desc_addr = vhost_iova_to_vva(dev, + vq, desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RO); if (unlikely(!desc_addr)) { error = -1; goto out; @@ -910,19 +852,37 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, nr_desc += 1; } else { desc_avail = desc->len - dev->vhost_hlen; - desc_offset = dev->vhost_hlen; + + if (unlikely(desc_chunck_len < dev->vhost_hlen)) { + desc_chunck_len = desc_avail; + desc_gaddr += dev->vhost_hlen; + desc_addr = vhost_iova_to_vva(dev, + vq, desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RO); + if (unlikely(!desc_addr)) { + error = -1; + goto out; + } + + desc_offset = 0; + } else { + desc_offset = dev->vhost_hlen; + desc_chunck_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)(desc_addr + desc_offset), + (uint32_t)desc_chunck_len, 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(desc_chunck_len, mbuf_avail); /* * A desc buf might across two host physical pages that are @@ -930,11 +890,12 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, * 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)))) { + desc_gaddr + desc_offset, cpy_len)))) { cur->data_len = cpy_len; cur->data_off = 0; - cur->buf_addr = (void *)(uintptr_t)desc_addr; - cur->buf_physaddr = hpa; + cur->buf_addr = (void *)(uintptr_t)(desc_addr + + desc_offset); + cur->buf_iova = hpa; /* * In zero copy mode, one mbuf can only reference data @@ -943,27 +904,31 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, 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) || + desc->len != desc_chunck_len)) { rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset), (void *)((uintptr_t)(desc_addr + desc_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 = + batch_copy[vq->batch_copy_nb_elems].src = (void *)((uintptr_t)(desc_addr + desc_offset)); - batch_copy[copy_nb].len = cpy_len; - copy_nb++; + 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_chunck_len -= cpy_len; desc_offset += cpy_len; /* This desc reaches to its end, get the next one */ @@ -982,7 +947,12 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, goto out; } - desc_addr = rte_vhost_gpa_to_vva(dev->mem, desc->addr); + desc_chunck_len = desc->len; + desc_gaddr = desc->addr; + desc_addr = vhost_iova_to_vva(dev, + vq, desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RO); if (unlikely(!desc_addr)) { error = -1; goto out; @@ -993,7 +963,23 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, desc_offset = 0; desc_avail = desc->len; - PRINT_PACKET(dev, (uintptr_t)desc_addr, desc->len, 0); + PRINT_PACKET(dev, (uintptr_t)desc_addr, + (uint32_t)desc_chunck_len, 0); + } else if (unlikely(desc_chunck_len == 0)) { + desc_chunck_len = desc_avail; + desc_gaddr += desc_offset; + desc_addr = vhost_iova_to_vva(dev, vq, + desc_gaddr, + &desc_chunck_len, + VHOST_ACCESS_RO); + if (unlikely(!desc_addr)) { + error = -1; + goto out; + } + desc_offset = 0; + + PRINT_PACKET(dev, (uintptr_t)desc_addr, + (uint32_t)desc_chunck_len, 0); } /* @@ -1029,42 +1015,10 @@ copy_desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq, 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)); - - /* Kick guest if required. */ - if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT) - && (vq->callfd >= 0)) - eventfd_write(vq->callfd, (eventfd_t)1); -} - static __rte_always_inline struct zcopy_mbuf * get_zmbuf(struct vhost_virtqueue *vq) { @@ -1108,6 +1062,22 @@ mbuf_is_consumed(struct rte_mbuf *m) return true; } +static __rte_always_inline void +restore_mbuf(struct rte_mbuf *m) +{ + uint32_t mbuf_size, priv_size; + + while (m) { + priv_size = rte_pktmbuf_priv_size(m->pool); + mbuf_size = sizeof(struct rte_mbuf) + priv_size; + /* start of buffer is after mbuf structure and priv data */ + + m->buf_addr = (char *)m + mbuf_size; + m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size; + m = m->next; + } +} + uint16_t rte_vhost_dequeue_burst(int vid, uint16_t queue_id, struct rte_mempool *mbuf_pool, struct rte_mbuf **pkts, uint16_t count) @@ -1116,7 +1086,6 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, 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; @@ -1125,6 +1094,13 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, if (!dev) return 0; + if (unlikely(!(dev->flags & VIRTIO_DEV_BUILTIN_VIRTIO_NET))) { + RTE_LOG(ERR, VHOST_DATA, + "(%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))) { RTE_LOG(ERR, VHOST_DATA, "(%d) %s: invalid virtqueue idx %d.\n", dev->vid, __func__, queue_id); @@ -1132,10 +1108,22 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, } vq = dev->virtqueue[queue_id]; - if (unlikely(vq->enabled == 0)) + + if (unlikely(rte_spinlock_trylock(&vq->access_lock) == 0)) return 0; + if (unlikely(vq->enabled == 0)) + goto out_access_unlock; + vq->batch_copy_nb_elems = 0; + vq->shadow_used_idx = 0; + + 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; if (unlikely(dev->dequeue_zero_copy)) { struct zcopy_mbuf *zmbuf, *next; @@ -1146,19 +1134,20 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, 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); + update_shadow_used_ring(vq, zmbuf->desc_idx, 0); nr_updated += 1; 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); + flush_shadow_used_ring(dev, vq); + vhost_vring_call(dev, vq); + vq->shadow_used_idx = 0; } /* @@ -1181,19 +1170,13 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, rte_atomic16_cmpset((volatile uint16_t *) &dev->broadcast_rarp.cnt, 1, 0))) { - rarp_mbuf = rte_pktmbuf_alloc(mbuf_pool); + rarp_mbuf = rte_net_make_rarp_packet(mbuf_pool, &dev->mac); if (rarp_mbuf == NULL) { RTE_LOG(ERR, VHOST_DATA, - "Failed to allocate memory for mbuf.\n"); + "Failed to make RARP packet.\n"); return 0; } - - if (make_rarp_packet(rarp_mbuf, &dev->mac)) { - rte_pktmbuf_free(rarp_mbuf); - rarp_mbuf = NULL; - } else { - count -= 1; - } + count -= 1; } free_entries = *((volatile uint16_t *)&vq->avail->idx) - @@ -1201,46 +1184,60 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, if (free_entries == 0) goto out; - LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__); + VHOST_LOG_DEBUG(VHOST_DATA, "(%d) %s\n", dev->vid, __func__); /* 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]); 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_DEBUG(VHOST_DATA, "(%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]); + update_shadow_used_ring(vq, desc_indexes[i], 0); } /* Prefetch descriptor index. */ rte_prefetch0(&vq->desc[desc_indexes[0]]); for (i = 0; i < count; i++) { - struct vring_desc *desc; + struct vring_desc *desc, *idesc = NULL; uint16_t sz, idx; + uint64_t dlen; 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) { + dlen = vq->desc[desc_indexes[i]].len; desc = (struct vring_desc *)(uintptr_t) - rte_vhost_gpa_to_vva(dev->mem, - vq->desc[desc_indexes[i]].addr); + vhost_iova_to_vva(dev, vq, + vq->desc[desc_indexes[i]].addr, + &dlen, + VHOST_ACCESS_RO); if (unlikely(!desc)) break; + if (unlikely(dlen < vq->desc[desc_indexes[i]].len)) { + /* + * The indirect desc table is not contiguous + * in process VA space, we have to copy it. + */ + idesc = alloc_copy_ind_table(dev, vq, + &vq->desc[desc_indexes[i]]); + if (unlikely(!idesc)) + break; + + desc = idesc; + } + rte_prefetch0(desc); sz = vq->desc[desc_indexes[i]].len / sizeof(*desc); idx = 0; @@ -1254,6 +1251,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, if (unlikely(pkts[i] == NULL)) { RTE_LOG(ERR, VHOST_DATA, "Failed to allocate memory for mbuf.\n"); + free_ind_table(idesc); break; } @@ -1261,6 +1259,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, mbuf_pool); if (unlikely(err)) { rte_pktmbuf_free(pkts[i]); + free_ind_table(idesc); break; } @@ -1270,6 +1269,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, zmbuf = get_zmbuf(vq); if (!zmbuf) { rte_pktmbuf_free(pkts[i]); + free_ind_table(idesc); break; } zmbuf->mbuf = pkts[i]; @@ -1286,16 +1286,27 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id, vq->nr_zmbuf += 1; TAILQ_INSERT_TAIL(&vq->zmbuf_list, zmbuf, next); } + + if (unlikely(!!idesc)) + free_ind_table(idesc); } vq->last_avail_idx += i; 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; + flush_shadow_used_ring(dev, vq); + vhost_vring_call(dev, vq); } 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