X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=9b99bf3eb803554a64437699a14cbedd33e715ea;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=371f170572cfc53f03af1c086d33caa4e565c4ec;hpb=5bdd24e451c711129218c88292cae8e891e7506a;p=dpdk.git diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c index 371f170572..9b99bf3eb8 100644 --- a/drivers/net/virtio/virtio_ethdev.c +++ b/drivers/net/virtio/virtio_ethdev.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 @@ -37,22 +8,27 @@ #include #include -#include +#include #include #include #include #include #include -#include #include #include +#include #include +#include +#include #include #include +#include #include #include #include +#include +#include #include "virtio_ethdev.h" #include "virtio_pci.h" @@ -72,11 +48,12 @@ static void virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info); static int virtio_dev_link_update(struct rte_eth_dev *dev, int wait_to_complete); +static int virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask); static void virtio_set_hwaddr(struct virtio_hw *hw); static void virtio_get_hwaddr(struct virtio_hw *hw); -static void virtio_dev_stats_get(struct rte_eth_dev *dev, +static int virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats); static int virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, unsigned n); @@ -88,11 +65,13 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev); static int virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on); static int virtio_mac_addr_add(struct rte_eth_dev *dev, - struct ether_addr *mac_addr, + struct rte_ether_addr *mac_addr, uint32_t index, uint32_t vmdq); static void virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index); -static void virtio_mac_addr_set(struct rte_eth_dev *dev, - struct ether_addr *mac_addr); +static int virtio_mac_addr_set(struct rte_eth_dev *dev, + struct rte_ether_addr *mac_addr); + +static int virtio_intr_disable(struct rte_eth_dev *dev); static int virtio_dev_queue_stats_mapping_set( struct rte_eth_dev *eth_dev, @@ -100,6 +79,12 @@ static int virtio_dev_queue_stats_mapping_set( uint8_t stat_idx, uint8_t is_rx); +int virtio_logtype_init; +int virtio_logtype_driver; + +static void virtio_notify_peers(struct rte_eth_dev *dev); +static void virtio_ack_link_announce(struct rte_eth_dev *dev); + /* * The set of PCI devices this driver supports */ @@ -155,34 +140,112 @@ static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = { struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS]; -static int -virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, - int *dlen, int pkt_num) +static struct virtio_pmd_ctrl * +virtio_send_command_packed(struct virtnet_ctl *cvq, + struct virtio_pmd_ctrl *ctrl, + int *dlen, int pkt_num) { - uint32_t head, i; - int k, sum = 0; - virtio_net_ctrl_ack status = ~0; - struct virtio_pmd_ctrl result; - struct virtqueue *vq; + struct virtqueue *vq = cvq->vq; + int head; + struct vring_packed_desc *desc = vq->vq_packed.ring.desc; + struct virtio_pmd_ctrl *result; + uint16_t flags; + int sum = 0; + int nb_descs = 0; + int k; - ctrl->status = status; + /* + * Format is enforced in qemu code: + * One TX packet for header; + * At least one TX packet per argument; + * One RX packet for ACK. + */ + head = vq->vq_avail_idx; + flags = vq->vq_packed.cached_flags; + desc[head].addr = cvq->virtio_net_hdr_mem; + desc[head].len = sizeof(struct virtio_net_ctrl_hdr); + vq->vq_free_cnt--; + nb_descs++; + 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; + } - if (!cvq || !cvq->vq) { - PMD_INIT_LOG(ERR, "Control queue is not supported."); - return -1; + for (k = 0; k < pkt_num; k++) { + desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem + + sizeof(struct virtio_net_ctrl_hdr) + + sizeof(ctrl->status) + sizeof(uint8_t) * sum; + desc[vq->vq_avail_idx].len = dlen[k]; + desc[vq->vq_avail_idx].flags = VRING_DESC_F_NEXT | + vq->vq_packed.cached_flags; + sum += dlen[k]; + vq->vq_free_cnt--; + nb_descs++; + 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 = cvq->vq; - head = vq->vq_desc_head_idx; - PMD_INIT_LOG(DEBUG, "vq->vq_desc_head_idx = %d, status = %d, " - "vq->hw->cvq = %p vq = %p", - vq->vq_desc_head_idx, status, vq->hw->cvq, vq); + desc[vq->vq_avail_idx].addr = cvq->virtio_net_hdr_mem + + sizeof(struct virtio_net_ctrl_hdr); + desc[vq->vq_avail_idx].len = sizeof(ctrl->status); + desc[vq->vq_avail_idx].flags = VRING_DESC_F_WRITE | + vq->vq_packed.cached_flags; + vq->vq_free_cnt--; + nb_descs++; + 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; + } - if ((vq->vq_free_cnt < ((uint32_t)pkt_num + 2)) || (pkt_num < 1)) - return -1; + virtio_wmb(vq->hw->weak_barriers); + desc[head].flags = VRING_DESC_F_NEXT | flags; - memcpy(cvq->virtio_net_hdr_mz->addr, ctrl, - sizeof(struct virtio_pmd_ctrl)); + virtio_wmb(vq->hw->weak_barriers); + virtqueue_notify(vq); + + /* wait for used descriptors in virtqueue */ + while (!desc_is_used(&desc[head], vq)) + usleep(100); + + virtio_rmb(vq->hw->weak_barriers); + + /* now get used descriptors */ + vq->vq_free_cnt += nb_descs; + vq->vq_used_cons_idx += nb_descs; + if (vq->vq_used_cons_idx >= vq->vq_nentries) { + vq->vq_used_cons_idx -= vq->vq_nentries; + vq->vq_packed.used_wrap_counter ^= 1; + } + + PMD_INIT_LOG(DEBUG, "vq->vq_free_cnt=%d\n" + "vq->vq_avail_idx=%d\n" + "vq->vq_used_cons_idx=%d\n" + "vq->vq_packed.cached_flags=0x%x\n" + "vq->vq_packed.used_wrap_counter=%d\n", + vq->vq_free_cnt, + vq->vq_avail_idx, + vq->vq_used_cons_idx, + vq->vq_packed.cached_flags, + vq->vq_packed.used_wrap_counter); + + result = cvq->virtio_net_hdr_mz->addr; + return result; +} + +static struct virtio_pmd_ctrl * +virtio_send_command_split(struct virtnet_ctl *cvq, + struct virtio_pmd_ctrl *ctrl, + int *dlen, int pkt_num) +{ + struct virtio_pmd_ctrl *result; + struct virtqueue *vq = cvq->vq; + uint32_t head, i; + int k, sum = 0; + + head = vq->vq_desc_head_idx; /* * Format is enforced in qemu code: @@ -190,30 +253,30 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, * At least one TX packet per argument; * One RX packet for ACK. */ - vq->vq_ring.desc[head].flags = VRING_DESC_F_NEXT; - vq->vq_ring.desc[head].addr = cvq->virtio_net_hdr_mem; - vq->vq_ring.desc[head].len = sizeof(struct virtio_net_ctrl_hdr); + vq->vq_split.ring.desc[head].flags = VRING_DESC_F_NEXT; + vq->vq_split.ring.desc[head].addr = cvq->virtio_net_hdr_mem; + vq->vq_split.ring.desc[head].len = sizeof(struct virtio_net_ctrl_hdr); vq->vq_free_cnt--; - i = vq->vq_ring.desc[head].next; + i = vq->vq_split.ring.desc[head].next; for (k = 0; k < pkt_num; k++) { - vq->vq_ring.desc[i].flags = VRING_DESC_F_NEXT; - vq->vq_ring.desc[i].addr = cvq->virtio_net_hdr_mem + vq->vq_split.ring.desc[i].flags = VRING_DESC_F_NEXT; + vq->vq_split.ring.desc[i].addr = cvq->virtio_net_hdr_mem + sizeof(struct virtio_net_ctrl_hdr) + sizeof(ctrl->status) + sizeof(uint8_t)*sum; - vq->vq_ring.desc[i].len = dlen[k]; + vq->vq_split.ring.desc[i].len = dlen[k]; sum += dlen[k]; vq->vq_free_cnt--; - i = vq->vq_ring.desc[i].next; + i = vq->vq_split.ring.desc[i].next; } - vq->vq_ring.desc[i].flags = VRING_DESC_F_WRITE; - vq->vq_ring.desc[i].addr = cvq->virtio_net_hdr_mem + vq->vq_split.ring.desc[i].flags = VRING_DESC_F_WRITE; + vq->vq_split.ring.desc[i].addr = cvq->virtio_net_hdr_mem + sizeof(struct virtio_net_ctrl_hdr); - vq->vq_ring.desc[i].len = sizeof(ctrl->status); + vq->vq_split.ring.desc[i].len = sizeof(ctrl->status); vq->vq_free_cnt--; - vq->vq_desc_head_idx = vq->vq_ring.desc[i].next; + vq->vq_desc_head_idx = vq->vq_split.ring.desc[i].next; vq_update_avail_ring(vq, head); vq_update_avail_idx(vq); @@ -234,16 +297,17 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, used_idx = (uint32_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]; idx = (uint32_t) uep->id; desc_idx = idx; - while (vq->vq_ring.desc[desc_idx].flags & VRING_DESC_F_NEXT) { - desc_idx = vq->vq_ring.desc[desc_idx].next; + while (vq->vq_split.ring.desc[desc_idx].flags & + VRING_DESC_F_NEXT) { + desc_idx = vq->vq_split.ring.desc[desc_idx].next; vq->vq_free_cnt++; } - vq->vq_ring.desc[desc_idx].next = vq->vq_desc_head_idx; + vq->vq_split.ring.desc[desc_idx].next = vq->vq_desc_head_idx; vq->vq_desc_head_idx = idx; vq->vq_used_cons_idx++; @@ -253,10 +317,47 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, PMD_INIT_LOG(DEBUG, "vq->vq_free_cnt=%d\nvq->vq_desc_head_idx=%d", vq->vq_free_cnt, vq->vq_desc_head_idx); - memcpy(&result, cvq->virtio_net_hdr_mz->addr, - sizeof(struct virtio_pmd_ctrl)); + result = cvq->virtio_net_hdr_mz->addr; + return result; +} - return result.status; +static int +virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, + int *dlen, int pkt_num) +{ + virtio_net_ctrl_ack status = ~0; + struct virtio_pmd_ctrl *result; + struct virtqueue *vq; + + ctrl->status = status; + + if (!cvq || !cvq->vq) { + PMD_INIT_LOG(ERR, "Control queue is not supported."); + return -1; + } + + rte_spinlock_lock(&cvq->lock); + vq = cvq->vq; + + PMD_INIT_LOG(DEBUG, "vq->vq_desc_head_idx = %d, status = %d, " + "vq->hw->cvq = %p vq = %p", + vq->vq_desc_head_idx, status, vq->hw->cvq, vq); + + if (vq->vq_free_cnt < pkt_num + 2 || pkt_num < 1) { + rte_spinlock_unlock(&cvq->lock); + return -1; + } + + memcpy(cvq->virtio_net_hdr_mz->addr, ctrl, + sizeof(struct virtio_pmd_ctrl)); + + if (vtpci_packed_queue(vq->hw)) + result = virtio_send_command_packed(cvq, ctrl, dlen, pkt_num); + else + result = virtio_send_command_split(cvq, ctrl, dlen, pkt_num); + + rte_spinlock_unlock(&cvq->lock); + return result->status; } static int @@ -289,17 +390,6 @@ virtio_dev_queue_release(void *queue __rte_unused) /* do nothing */ } -static int -virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx) -{ - if (vtpci_queue_idx == hw->max_queue_pairs * 2) - return VTNET_CQ; - else if (vtpci_queue_idx % 2 == 0) - return VTNET_RQ; - else - return VTNET_TQ; -} - static uint16_t virtio_get_nr_vq(struct virtio_hw *hw) { @@ -315,25 +405,28 @@ static void virtio_init_vring(struct virtqueue *vq) { int size = vq->vq_nentries; - struct vring *vr = &vq->vq_ring; uint8_t *ring_mem = vq->vq_ring_virt_mem; PMD_INIT_FUNC_TRACE(); - /* - * Reinitialise since virtio port might have been stopped and restarted - */ memset(ring_mem, 0, vq->vq_ring_size); - vring_init(vr, size, ring_mem, VIRTIO_PCI_VRING_ALIGN); + vq->vq_used_cons_idx = 0; vq->vq_desc_head_idx = 0; vq->vq_avail_idx = 0; vq->vq_desc_tail_idx = (uint16_t)(vq->vq_nentries - 1); vq->vq_free_cnt = vq->vq_nentries; memset(vq->vq_descx, 0, sizeof(struct vq_desc_extra) * vq->vq_nentries); + if (vtpci_packed_queue(vq->hw)) { + vring_init_packed(&vq->vq_packed.ring, ring_mem, + VIRTIO_PCI_VRING_ALIGN, size); + vring_desc_init_packed(vq, size); + } else { + struct vring *vr = &vq->vq_split.ring; - vring_desc_init(vr->desc, size); - + vring_init_split(vr, ring_mem, VIRTIO_PCI_VRING_ALIGN, size); + vring_desc_init_split(vr->desc, size); + } /* * Disable device(host) interrupting guest */ @@ -356,8 +449,10 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) void *sw_ring = NULL; int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx); int ret; + int numa_node = dev->device->numa_node; - PMD_INIT_LOG(DEBUG, "setting up queue: %u", vtpci_queue_idx); + PMD_INIT_LOG(INFO, "setting up queue: %u on NUMA node %d", + vtpci_queue_idx, numa_node); /* * Read the virtqueue size from the Queue Size field @@ -393,7 +488,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) } vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE, - SOCKET_ID_ANY); + numa_node); if (vq == NULL) { PMD_INIT_LOG(ERR, "can not allocate vq"); return -ENOMEM; @@ -403,18 +498,25 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) vq->hw = hw; vq->vq_queue_index = vtpci_queue_idx; vq->vq_nentries = vq_size; + if (vtpci_packed_queue(hw)) { + vq->vq_packed.used_wrap_counter = 1; + vq->vq_packed.cached_flags = VRING_PACKED_DESC_F_AVAIL; + vq->vq_packed.event_flags_shadow = 0; + if (queue_type == VTNET_RQ) + vq->vq_packed.cached_flags |= VRING_DESC_F_WRITE; + } /* * Reserve a memzone for vring elements */ - size = vring_size(vq_size, VIRTIO_PCI_VRING_ALIGN); + size = vring_size(hw, vq_size, VIRTIO_PCI_VRING_ALIGN); vq->vq_ring_size = RTE_ALIGN_CEIL(size, VIRTIO_PCI_VRING_ALIGN); PMD_INIT_LOG(DEBUG, "vring_size: %d, rounded_vring_size: %d", size, vq->vq_ring_size); mz = rte_memzone_reserve_aligned(vq_name, vq->vq_ring_size, - SOCKET_ID_ANY, - 0, VIRTIO_PCI_VRING_ALIGN); + numa_node, RTE_MEMZONE_IOVA_CONTIG, + VIRTIO_PCI_VRING_ALIGN); if (mz == NULL) { if (rte_errno == EEXIST) mz = rte_memzone_lookup(vq_name); @@ -426,10 +528,10 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) memset(mz->addr, 0, mz->len); - vq->vq_ring_mem = mz->phys_addr; + vq->vq_ring_mem = mz->iova; vq->vq_ring_virt_mem = mz->addr; PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem: 0x%" PRIx64, - (uint64_t)mz->phys_addr); + (uint64_t)mz->iova); PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%" PRIx64, (uint64_t)(uintptr_t)mz->addr); @@ -439,8 +541,8 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) snprintf(vq_hdr_name, sizeof(vq_hdr_name), "port%d_vq%d_hdr", dev->data->port_id, vtpci_queue_idx); hdr_mz = rte_memzone_reserve_aligned(vq_hdr_name, sz_hdr_mz, - SOCKET_ID_ANY, 0, - RTE_CACHE_LINE_SIZE); + numa_node, RTE_MEMZONE_IOVA_CONTIG, + RTE_CACHE_LINE_SIZE); if (hdr_mz == NULL) { if (rte_errno == EEXIST) hdr_mz = rte_memzone_lookup(vq_hdr_name); @@ -456,7 +558,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) sizeof(vq->sw_ring[0]); sw_ring = rte_zmalloc_socket("sw_ring", sz_sw, - RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY); + RTE_CACHE_LINE_SIZE, numa_node); if (!sw_ring) { PMD_INIT_LOG(ERR, "can not allocate RX soft ring"); ret = -ENOMEM; @@ -474,13 +576,13 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) txvq->port_id = dev->data->port_id; txvq->mz = mz; txvq->virtio_net_hdr_mz = hdr_mz; - txvq->virtio_net_hdr_mem = hdr_mz->phys_addr; + txvq->virtio_net_hdr_mem = hdr_mz->iova; } else if (queue_type == VTNET_CQ) { cvq = &vq->cq; cvq->vq = vq; cvq->mz = mz; cvq->virtio_net_hdr_mz = hdr_mz; - cvq->virtio_net_hdr_mem = hdr_mz->phys_addr; + cvq->virtio_net_hdr_mem = hdr_mz->iova; memset(cvq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE); hw->cvq = cvq; @@ -491,7 +593,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) * VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information. */ if (!hw->virtio_user_dev) - vq->offset = offsetof(struct rte_mbuf, buf_physaddr); + vq->offset = offsetof(struct rte_mbuf, buf_iova); else { vq->vq_ring_mem = (uintptr_t)mz->addr; vq->offset = offsetof(struct rte_mbuf, buf_addr); @@ -510,15 +612,17 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) for (i = 0; i < vq_size; i++) { struct vring_desc *start_dp = txr[i].tx_indir; - vring_desc_init(start_dp, RTE_DIM(txr[i].tx_indir)); - /* first indirect descriptor is always the tx header */ - start_dp->addr = txvq->virtio_net_hdr_mem - + i * sizeof(*txr) - + offsetof(struct virtio_tx_region, tx_hdr); - - start_dp->len = hw->vtnet_hdr_size; - start_dp->flags = VRING_DESC_F_NEXT; + if (!vtpci_packed_queue(hw)) { + vring_desc_init_split(start_dp, + RTE_DIM(txr[i].tx_indir)); + start_dp->addr = txvq->virtio_net_hdr_mem + + i * sizeof(*txr) + + offsetof(struct virtio_tx_region, + tx_hdr); + start_dp->len = hw->vtnet_hdr_size; + start_dp->flags = VRING_DESC_F_NEXT; + } } } @@ -609,6 +713,10 @@ virtio_dev_close(struct rte_eth_dev *dev) PMD_INIT_LOG(DEBUG, "virtio_dev_close"); + if (!hw->opened) + return; + hw->opened = false; + /* reset the NIC */ if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) VTPCI_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR); @@ -616,7 +724,7 @@ virtio_dev_close(struct rte_eth_dev *dev) virtio_queues_unbind_intr(dev); if (intr_conf->lsc || intr_conf->rxq) { - rte_intr_disable(dev->intr_handle); + virtio_intr_disable(dev); rte_intr_efd_disable(dev->intr_handle); rte_free(dev->intr_handle->intr_vec); dev->intr_handle->intr_vec = NULL; @@ -742,10 +850,12 @@ virtio_mtu_set(struct rte_eth_dev *dev, uint16_t mtu) static int virtio_dev_rx_queue_intr_enable(struct rte_eth_dev *dev, uint16_t queue_id) { + struct virtio_hw *hw = dev->data->dev_private; struct virtnet_rx *rxvq = dev->data->rx_queues[queue_id]; struct virtqueue *vq = rxvq->vq; virtqueue_enable_intr(vq); + virtio_mb(hw->weak_barriers); return 0; } @@ -779,6 +889,7 @@ static const struct eth_dev_ops virtio_eth_dev_ops = { .stats_reset = virtio_dev_stats_reset, .xstats_reset = virtio_dev_stats_reset, .link_update = virtio_dev_link_update, + .vlan_offload_set = virtio_dev_vlan_offload_set, .rx_queue_setup = virtio_dev_rx_queue_setup, .rx_queue_intr_enable = virtio_dev_rx_queue_intr_enable, .rx_queue_intr_disable = virtio_dev_rx_queue_intr_disable, @@ -794,45 +905,20 @@ static const struct eth_dev_ops virtio_eth_dev_ops = { .mac_addr_set = virtio_mac_addr_set, }; -static inline int -virtio_dev_atomic_read_link_status(struct rte_eth_dev *dev, - struct rte_eth_link *link) -{ - struct rte_eth_link *dst = link; - struct rte_eth_link *src = &(dev->data->dev_link); - - if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, - *(uint64_t *)src) == 0) - return -1; - - return 0; -} - -/** - * Atomically writes the link status information into global - * structure rte_eth_dev. - * - * @param dev - * - Pointer to the structure rte_eth_dev to read from. - * - Pointer to the buffer to be saved with the link status. - * - * @return - * - On success, zero. - * - On failure, negative value. +/* + * dev_ops for virtio-user in secondary processes, as we just have + * some limited supports currently. */ -static inline int -virtio_dev_atomic_write_link_status(struct rte_eth_dev *dev, - struct rte_eth_link *link) -{ - struct rte_eth_link *dst = &(dev->data->dev_link); - struct rte_eth_link *src = link; - - if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, - *(uint64_t *)src) == 0) - return -1; - - return 0; -} +const struct eth_dev_ops virtio_user_secondary_eth_dev_ops = { + .dev_infos_get = virtio_dev_info_get, + .stats_get = virtio_dev_stats_get, + .xstats_get = virtio_dev_xstats_get, + .xstats_get_names = virtio_dev_xstats_get_names, + .stats_reset = virtio_dev_stats_reset, + .xstats_reset = virtio_dev_stats_reset, + /* collect stats per queue */ + .queue_stats_mapping_set = virtio_dev_queue_stats_mapping_set, +}; static void virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats) @@ -887,7 +973,7 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev, /* Note: limit checked in rte_eth_xstats_names() */ for (i = 0; i < dev->data->nb_rx_queues; i++) { - struct virtqueue *rxvq = dev->data->rx_queues[i]; + struct virtnet_rx *rxvq = dev->data->rx_queues[i]; if (rxvq == NULL) continue; for (t = 0; t < VIRTIO_NB_RXQ_XSTATS; t++) { @@ -900,7 +986,7 @@ static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev, } for (i = 0; i < dev->data->nb_tx_queues; i++) { - struct virtqueue *txvq = dev->data->tx_queues[i]; + struct virtnet_tx *txvq = dev->data->tx_queues[i]; if (txvq == NULL) continue; for (t = 0; t < VIRTIO_NB_TXQ_XSTATS; t++) { @@ -964,10 +1050,12 @@ virtio_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, return count; } -static void +static int virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) { virtio_update_stats(dev, stats); + + return 0; } static void @@ -1054,11 +1142,11 @@ virtio_mac_table_set(struct virtio_hw *hw, } static int -virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr, +virtio_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr, uint32_t index, uint32_t vmdq __rte_unused) { struct virtio_hw *hw = dev->data->dev_private; - const struct ether_addr *addrs = dev->data->mac_addrs; + const struct rte_ether_addr *addrs = dev->data->mac_addrs; unsigned int i; struct virtio_net_ctrl_mac *uc, *mc; @@ -1073,7 +1161,7 @@ virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr, mc->entries = 0; for (i = 0; i < VIRTIO_MAX_MAC_ADDRS; i++) { - const struct ether_addr *addr + const struct rte_ether_addr *addr = (i == index) ? mac_addr : addrs + i; struct virtio_net_ctrl_mac *tbl = is_multicast_ether_addr(addr) ? mc : uc; @@ -1088,7 +1176,7 @@ static void virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index) { struct virtio_hw *hw = dev->data->dev_private; - struct ether_addr *addrs = dev->data->mac_addrs; + struct rte_ether_addr *addrs = dev->data->mac_addrs; struct virtio_net_ctrl_mac *uc, *mc; unsigned int i; @@ -1115,8 +1203,8 @@ virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index) virtio_mac_table_set(hw, uc, mc); } -static void -virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) +static int +virtio_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) { struct virtio_hw *hw = dev->data->dev_private; @@ -1131,9 +1219,14 @@ virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET; memcpy(ctrl.data, mac_addr, ETHER_ADDR_LEN); - virtio_send_command(hw->cvq, &ctrl, &len, 1); - } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MAC)) - virtio_set_hwaddr(hw); + return virtio_send_command(hw->cvq, &ctrl, &len, 1); + } + + if (!vtpci_with_feature(hw, VIRTIO_NET_F_MAC)) + return -ENOTSUP; + + virtio_set_hwaddr(hw); + return 0; } static int @@ -1154,6 +1247,34 @@ virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) return virtio_send_command(hw->cvq, &ctrl, &len, 1); } +static int +virtio_intr_enable(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + + if (rte_intr_enable(dev->intr_handle) < 0) + return -1; + + if (!hw->virtio_user_dev) + hw->use_msix = vtpci_msix_detect(RTE_ETH_DEV_TO_PCI(dev)); + + return 0; +} + +static int +virtio_intr_disable(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + + if (rte_intr_disable(dev->intr_handle) < 0) + return -1; + + if (!hw->virtio_user_dev) + hw->use_msix = vtpci_msix_detect(RTE_ETH_DEV_TO_PCI(dev)); + + return 0; +} + static int virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) { @@ -1208,9 +1329,104 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) return 0; } +int +virtio_dev_pause(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + + rte_spinlock_lock(&hw->state_lock); + + if (hw->started == 0) { + /* Device is just stopped. */ + rte_spinlock_unlock(&hw->state_lock); + return -1; + } + hw->started = 0; + /* + * Prevent the worker threads from touching queues to avoid contention, + * 1 ms should be enough for the ongoing Tx function to finish. + */ + rte_delay_ms(1); + return 0; +} + +/* + * Recover hw state to let the worker threads continue. + */ +void +virtio_dev_resume(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + + hw->started = 1; + rte_spinlock_unlock(&hw->state_lock); +} + +/* + * Should be called only after device is paused. + */ +int +virtio_inject_pkts(struct rte_eth_dev *dev, struct rte_mbuf **tx_pkts, + int nb_pkts) +{ + struct virtio_hw *hw = dev->data->dev_private; + struct virtnet_tx *txvq = dev->data->tx_queues[0]; + int ret; + + hw->inject_pkts = tx_pkts; + ret = dev->tx_pkt_burst(txvq, tx_pkts, nb_pkts); + hw->inject_pkts = NULL; + + return ret; +} + +static void +virtio_notify_peers(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + struct virtnet_rx *rxvq; + struct rte_mbuf *rarp_mbuf; + + if (!dev->data->rx_queues) + return; + + rxvq = dev->data->rx_queues[0]; + if (!rxvq) + return; + + rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool, + (struct rte_ether_addr *)hw->mac_addr); + if (rarp_mbuf == NULL) { + PMD_DRV_LOG(ERR, "failed to make RARP packet."); + return; + } + + /* If virtio port just stopped, no need to send RARP */ + if (virtio_dev_pause(dev) < 0) { + rte_pktmbuf_free(rarp_mbuf); + return; + } + + virtio_inject_pkts(dev, &rarp_mbuf, 1); + virtio_dev_resume(dev); +} + +static void +virtio_ack_link_announce(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + struct virtio_pmd_ctrl ctrl; + + ctrl.hdr.class = VIRTIO_NET_CTRL_ANNOUNCE; + ctrl.hdr.cmd = VIRTIO_NET_CTRL_ANNOUNCE_ACK; + + virtio_send_command(hw->cvq, &ctrl, NULL, 0); +} + /* - * Process Virtio Config changed interrupt and call the callback - * if link state changed. + * Process virtio config changed interrupt. Call the callback + * if link state changed, generate gratuitous RARP packet if + * the status indicates an ANNOUNCE. */ void virtio_interrupt_handler(void *param) @@ -1218,30 +1434,93 @@ virtio_interrupt_handler(void *param) struct rte_eth_dev *dev = param; struct virtio_hw *hw = dev->data->dev_private; uint8_t isr; + uint16_t status; /* Read interrupt status which clears interrupt */ isr = vtpci_isr(hw); PMD_DRV_LOG(INFO, "interrupt status = %#x", isr); - if (rte_intr_enable(dev->intr_handle) < 0) + if (virtio_intr_enable(dev) < 0) PMD_DRV_LOG(ERR, "interrupt enable failed"); if (isr & VIRTIO_PCI_ISR_CONFIG) { if (virtio_dev_link_update(dev, 0) == 0) _rte_eth_dev_callback_process(dev, - RTE_ETH_EVENT_INTR_LSC, NULL); - } + RTE_ETH_EVENT_INTR_LSC, + NULL); + if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { + vtpci_read_dev_config(hw, + offsetof(struct virtio_net_config, status), + &status, sizeof(status)); + if (status & VIRTIO_NET_S_ANNOUNCE) { + virtio_notify_peers(dev); + if (hw->cvq) + virtio_ack_link_announce(dev); + } + } + } } +/* set rx and tx handlers according to what is supported */ static void -rx_func_get(struct rte_eth_dev *eth_dev) +set_rxtx_funcs(struct rte_eth_dev *eth_dev) { struct virtio_hw *hw = eth_dev->data->dev_private; - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) - eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts; - else - eth_dev->rx_pkt_burst = &virtio_recv_pkts; + + if (vtpci_packed_queue(hw)) { + PMD_INIT_LOG(INFO, + "virtio: using packed ring %s Tx path on port %u", + hw->use_inorder_tx ? "inorder" : "standard", + eth_dev->data->port_id); + eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed; + } else { + if (hw->use_inorder_tx) { + PMD_INIT_LOG(INFO, "virtio: using inorder Tx path on port %u", + eth_dev->data->port_id); + eth_dev->tx_pkt_burst = virtio_xmit_pkts_inorder; + } else { + PMD_INIT_LOG(INFO, "virtio: using standard Tx path on port %u", + eth_dev->data->port_id); + eth_dev->tx_pkt_burst = virtio_xmit_pkts; + } + } + + if (vtpci_packed_queue(hw)) { + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + PMD_INIT_LOG(INFO, + "virtio: using packed ring mergeable buffer Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = + &virtio_recv_mergeable_pkts_packed; + } else { + PMD_INIT_LOG(INFO, + "virtio: using packed ring standard Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = &virtio_recv_pkts_packed; + } + } else { + if (hw->use_simple_rx) { + PMD_INIT_LOG(INFO, "virtio: using simple Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = virtio_recv_pkts_vec; + } else if (hw->use_inorder_rx) { + PMD_INIT_LOG(INFO, + "virtio: using inorder Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = &virtio_recv_pkts_inorder; + } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + PMD_INIT_LOG(INFO, + "virtio: using mergeable buffer Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts; + } else { + PMD_INIT_LOG(INFO, "virtio: using standard Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = &virtio_recv_pkts; + } + } + } /* Only support 1:1 queue/interrupt mapping so far. @@ -1320,7 +1599,7 @@ virtio_configure_intr(struct rte_eth_dev *dev) * to change the config size from 20 to 24, or VIRTIO_MSI_QUEUE_VECTOR * (22) will be ignored. */ - if (rte_intr_enable(dev->intr_handle) < 0) { + if (virtio_intr_enable(dev) < 0) { PMD_DRV_LOG(ERR, "interrupt enable failed"); return -1; } @@ -1346,6 +1625,11 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) /* Reset the device although not necessary at startup */ vtpci_reset(hw); + if (hw->vqs) { + virtio_dev_free_mbufs(eth_dev); + virtio_free_queues(hw); + } + /* Tell the host we've noticed this device. */ vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_ACK); @@ -1354,30 +1638,31 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) if (virtio_negotiate_features(hw, req_features) < 0) return -1; + hw->weak_barriers = !vtpci_with_feature(hw, VIRTIO_F_ORDER_PLATFORM); + if (!hw->virtio_user_dev) { pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev); rte_eth_copy_pci_info(eth_dev, pci_dev); } - eth_dev->data->dev_flags = RTE_ETH_DEV_DETACHABLE; /* If host does not support both status and MSI-X then disable LSC */ - if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS) && hw->use_msix) + if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS) && + hw->use_msix != VIRTIO_MSIX_NONE) eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC; else eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC; - rx_func_get(eth_dev); - /* Setting up rx_header size for the device */ if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) || - vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) + vtpci_with_feature(hw, VIRTIO_F_VERSION_1) || + vtpci_with_feature(hw, VIRTIO_F_RING_PACKED)) hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf); else hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr); /* Copy the permanent MAC address to: virtio_hw */ virtio_get_hwaddr(hw); - ether_addr_copy((struct ether_addr *) hw->mac_addr, + ether_addr_copy((struct rte_ether_addr *)hw->mac_addr, ð_dev->data->mac_addrs[0]); PMD_INIT_LOG(DEBUG, "PORT MAC: %02X:%02X:%02X:%02X:%02X:%02X", @@ -1451,6 +1736,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) } else { PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=1"); hw->max_queue_pairs = 1; + hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN - + VLAN_TAG_LEN - hw->vtnet_hdr_size; } ret = virtio_alloc_queues(eth_dev); @@ -1533,7 +1820,6 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) RTE_BUILD_BUG_ON(RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr_mrg_rxbuf)); eth_dev->dev_ops = &virtio_eth_dev_ops; - eth_dev->tx_pkt_burst = &virtio_xmit_pkts; if (rte_eal_process_type() == RTE_PROC_SECONDARY) { if (!hw->virtio_user_dev) { @@ -1543,12 +1829,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) } virtio_set_vtpci_ops(hw); - if (hw->use_simple_rxtx) { - eth_dev->tx_pkt_burst = virtio_xmit_pkts_simple; - eth_dev->rx_pkt_burst = virtio_recv_pkts_vec; - } else { - rx_func_get(eth_dev); - } + set_rxtx_funcs(eth_dev); + return 0; } @@ -1568,20 +1850,20 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) if (!hw->virtio_user_dev) { ret = vtpci_init(RTE_ETH_DEV_TO_PCI(eth_dev), hw); if (ret) - return ret; + goto out; } /* reset device and negotiate default features */ ret = virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES); if (ret < 0) - return ret; - - /* Setup interrupt callback */ - if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) - rte_intr_callback_register(eth_dev->intr_handle, - virtio_interrupt_handler, eth_dev); + goto out; return 0; + +out: + rte_free(eth_dev->data->mac_addrs); + eth_dev->data->mac_addrs = NULL; + return ret; } static int @@ -1590,7 +1872,7 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev) PMD_INIT_FUNC_TRACE(); if (rte_eal_process_type() == RTE_PROC_SECONDARY) - return -EPERM; + return 0; virtio_dev_stop(eth_dev); virtio_dev_close(eth_dev); @@ -1599,14 +1881,6 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev) eth_dev->tx_pkt_burst = NULL; eth_dev->rx_pkt_burst = NULL; - rte_free(eth_dev->data->mac_addrs); - eth_dev->data->mac_addrs = NULL; - - /* reset interrupt callback */ - if (eth_dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) - rte_intr_callback_unregister(eth_dev->intr_handle, - virtio_interrupt_handler, - eth_dev); if (eth_dev->device) rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev)); @@ -1615,9 +1889,56 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev) return 0; } +static int vdpa_check_handler(__rte_unused const char *key, + const char *value, __rte_unused void *opaque) +{ + if (strcmp(value, "1")) + return -1; + + return 0; +} + +static int +vdpa_mode_selected(struct rte_devargs *devargs) +{ + struct rte_kvargs *kvlist; + const char *key = "vdpa"; + int ret = 0; + + if (devargs == NULL) + return 0; + + kvlist = rte_kvargs_parse(devargs->args, NULL); + if (kvlist == NULL) + return 0; + + if (!rte_kvargs_count(kvlist, key)) + goto exit; + + /* vdpa mode selected when there's a key-value pair: vdpa=1 */ + if (rte_kvargs_process(kvlist, key, + vdpa_check_handler, NULL) < 0) { + goto exit; + } + ret = 1; + +exit: + rte_kvargs_free(kvlist); + return ret; +} + static int eth_virtio_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct rte_pci_device *pci_dev) { + if (rte_eal_iopl_init() != 0) { + PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD"); + return 1; + } + + /* virtio pmd skips probe if device needs to work in vdpa mode */ + if (vdpa_mode_selected(pci_dev->device.devargs)) + return 1; + return rte_eth_dev_pci_generic_probe(pci_dev, sizeof(struct virtio_hw), eth_virtio_dev_init); } @@ -1637,18 +1958,28 @@ static struct rte_pci_driver rte_virtio_pmd = { .remove = eth_virtio_pci_remove, }; -RTE_INIT(rte_virtio_pmd_init); -static void -rte_virtio_pmd_init(void) +RTE_INIT(rte_virtio_pmd_init) { - if (rte_eal_iopl_init() != 0) { - PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD"); - return; - } - + rte_eal_iopl_init(); rte_pci_register(&rte_virtio_pmd); } +static bool +rx_offload_enabled(struct virtio_hw *hw) +{ + return vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM) || + vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) || + vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6); +} + +static bool +tx_offload_enabled(struct virtio_hw *hw) +{ + return vtpci_with_feature(hw, VIRTIO_NET_F_CSUM) || + vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO4) || + vtpci_with_feature(hw, VIRTIO_NET_F_HOST_TSO6); +} + /* * Configure virtio device * It returns 0 on success. @@ -1657,19 +1988,45 @@ static int virtio_dev_configure(struct rte_eth_dev *dev) { const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode; + const struct rte_eth_txmode *txmode = &dev->data->dev_conf.txmode; struct virtio_hw *hw = dev->data->dev_private; + uint32_t ether_hdr_len = ETHER_HDR_LEN + VLAN_TAG_LEN + + hw->vtnet_hdr_size; + uint64_t rx_offloads = rxmode->offloads; + uint64_t tx_offloads = txmode->offloads; uint64_t req_features; int ret; PMD_INIT_LOG(DEBUG, "configure"); req_features = VIRTIO_PMD_DEFAULT_GUEST_FEATURES; - if (rxmode->hw_ip_checksum) + + if (dev->data->dev_conf.intr_conf.rxq) { + ret = virtio_init_device(dev, hw->req_guest_features); + if (ret < 0) + return ret; + } + + if (rxmode->max_rx_pkt_len > hw->max_mtu + ether_hdr_len) + req_features &= ~(1ULL << VIRTIO_NET_F_MTU); + + if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM | + DEV_RX_OFFLOAD_TCP_CKSUM)) req_features |= (1ULL << VIRTIO_NET_F_GUEST_CSUM); - if (rxmode->enable_lro) + + if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) req_features |= (1ULL << VIRTIO_NET_F_GUEST_TSO4) | (1ULL << VIRTIO_NET_F_GUEST_TSO6); + if (tx_offloads & (DEV_TX_OFFLOAD_UDP_CKSUM | + DEV_TX_OFFLOAD_TCP_CKSUM)) + req_features |= (1ULL << VIRTIO_NET_F_CSUM); + + if (tx_offloads & DEV_TX_OFFLOAD_TCP_TSO) + req_features |= + (1ULL << VIRTIO_NET_F_HOST_TSO4) | + (1ULL << VIRTIO_NET_F_HOST_TSO6); + /* if request features changed, reinit the device */ if (req_features != hw->req_guest_features) { ret = virtio_init_device(dev, req_features); @@ -1677,18 +2034,19 @@ virtio_dev_configure(struct rte_eth_dev *dev) return ret; } - if (rxmode->hw_ip_checksum && + if ((rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM | + DEV_RX_OFFLOAD_TCP_CKSUM)) && !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) { - PMD_DRV_LOG(NOTICE, - "rx ip checksum not available on this host"); + PMD_DRV_LOG(ERR, + "rx checksum not available on this host"); return -ENOTSUP; } - if (rxmode->enable_lro && + if ((rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) && (!vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) || - !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4))) { - PMD_DRV_LOG(NOTICE, - "lro not available on this host"); + !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6))) { + PMD_DRV_LOG(ERR, + "Large Receive Offload not available on this host"); return -ENOTSUP; } @@ -1696,15 +2054,19 @@ virtio_dev_configure(struct rte_eth_dev *dev) if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) virtio_dev_cq_start(dev); - hw->vlan_strip = rxmode->hw_vlan_strip; + if (rx_offloads & DEV_RX_OFFLOAD_VLAN_STRIP) + hw->vlan_strip = 1; - if (rxmode->hw_vlan_filter + if ((rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER) && !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { - PMD_DRV_LOG(NOTICE, + PMD_DRV_LOG(ERR, "vlan filtering not available on this host"); return -ENOTSUP; } + hw->has_tx_offload = tx_offload_enabled(hw); + hw->has_rx_offload = rx_offload_enabled(hw); + if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) /* Enable vector (0) for Link State Intrerrupt */ if (VTPCI_OPS(hw)->set_config_irq(hw, 0) == @@ -1713,6 +2075,38 @@ virtio_dev_configure(struct rte_eth_dev *dev) return -EBUSY; } + rte_spinlock_init(&hw->state_lock); + + hw->use_simple_rx = 1; + + if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) { + hw->use_inorder_tx = 1; + hw->use_inorder_rx = 1; + hw->use_simple_rx = 0; + } + + if (vtpci_packed_queue(hw)) { + hw->use_simple_rx = 0; + hw->use_inorder_rx = 0; + } + +#if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM + if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) { + hw->use_simple_rx = 0; + } +#endif + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + hw->use_simple_rx = 0; + } + + if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM | + DEV_RX_OFFLOAD_TCP_CKSUM | + DEV_RX_OFFLOAD_TCP_LRO | + DEV_RX_OFFLOAD_VLAN_STRIP)) + hw->use_simple_rx = 0; + + hw->opened = true; + return 0; } @@ -1724,6 +2118,19 @@ virtio_dev_start(struct rte_eth_dev *dev) struct virtnet_rx *rxvq; struct virtnet_tx *txvq __rte_unused; struct virtio_hw *hw = dev->data->dev_private; + int ret; + + /* Finish the initialization of the queues */ + for (i = 0; i < dev->data->nb_rx_queues; i++) { + ret = virtio_dev_rx_queue_setup_finish(dev, i); + if (ret < 0) + return ret; + } + for (i = 0; i < dev->data->nb_tx_queues; i++) { + ret = virtio_dev_tx_queue_setup_finish(dev, i); + if (ret < 0) + return ret; + } /* check if lsc interrupt feature is enabled */ if (dev->data->dev_conf.intr_conf.lsc) { @@ -1739,9 +2146,15 @@ virtio_dev_start(struct rte_eth_dev *dev) */ if (dev->data->dev_conf.intr_conf.lsc || dev->data->dev_conf.intr_conf.rxq) { - rte_intr_disable(dev->intr_handle); + virtio_intr_disable(dev); - if (rte_intr_enable(dev->intr_handle) < 0) { + /* Setup interrupt callback */ + if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) + rte_intr_callback_register(dev->intr_handle, + virtio_interrupt_handler, + dev); + + if (virtio_intr_enable(dev) < 0) { PMD_DRV_LOG(ERR, "interrupt enable failed"); return -EIO; } @@ -1761,9 +2174,16 @@ virtio_dev_start(struct rte_eth_dev *dev) for (i = 0; i < dev->data->nb_rx_queues; i++) { rxvq = dev->data->rx_queues[i]; + /* Flush the old packets */ + virtqueue_rxvq_flush(rxvq->vq); virtqueue_notify(rxvq->vq); } + for (i = 0; i < dev->data->nb_tx_queues; i++) { + txvq = dev->data->tx_queues[i]; + virtqueue_notify(txvq->vq); + } + PMD_INIT_LOG(DEBUG, "Notified backend at initialization"); for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -1776,7 +2196,8 @@ virtio_dev_start(struct rte_eth_dev *dev) VIRTQUEUE_DUMP(txvq->vq); } - hw->started = 1; + set_rxtx_funcs(dev); + hw->started = true; /* Initialize Link state */ virtio_dev_link_update(dev, 0); @@ -1786,47 +2207,47 @@ virtio_dev_start(struct rte_eth_dev *dev) static void virtio_dev_free_mbufs(struct rte_eth_dev *dev) { + struct virtio_hw *hw = dev->data->dev_private; + uint16_t nr_vq = virtio_get_nr_vq(hw); + const char *type __rte_unused; + unsigned int i, mbuf_num = 0; + struct virtqueue *vq; struct rte_mbuf *buf; - int i, mbuf_num = 0; - - for (i = 0; i < dev->data->nb_rx_queues; i++) { - struct virtnet_rx *rxvq = dev->data->rx_queues[i]; - - PMD_INIT_LOG(DEBUG, - "Before freeing rxq[%d] used and unused buf", i); - VIRTQUEUE_DUMP(rxvq->vq); + int queue_type; - PMD_INIT_LOG(DEBUG, "rx_queues[%d]=%p", i, rxvq); - while ((buf = virtqueue_detatch_unused(rxvq->vq)) != NULL) { - rte_pktmbuf_free(buf); - mbuf_num++; - } + if (hw->vqs == NULL) + return; - PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num); - PMD_INIT_LOG(DEBUG, - "After freeing rxq[%d] used and unused buf", i); - VIRTQUEUE_DUMP(rxvq->vq); - } + for (i = 0; i < nr_vq; i++) { + vq = hw->vqs[i]; + if (!vq) + continue; - for (i = 0; i < dev->data->nb_tx_queues; i++) { - struct virtnet_tx *txvq = dev->data->tx_queues[i]; + queue_type = virtio_get_queue_type(hw, i); + if (queue_type == VTNET_RQ) + type = "rxq"; + else if (queue_type == VTNET_TQ) + type = "txq"; + else + continue; PMD_INIT_LOG(DEBUG, - "Before freeing txq[%d] used and unused bufs", - i); - VIRTQUEUE_DUMP(txvq->vq); + "Before freeing %s[%d] used and unused buf", + type, i); + VIRTQUEUE_DUMP(vq); - mbuf_num = 0; - while ((buf = virtqueue_detatch_unused(txvq->vq)) != NULL) { + while ((buf = virtqueue_detach_unused(vq)) != NULL) { rte_pktmbuf_free(buf); mbuf_num++; } - PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num); PMD_INIT_LOG(DEBUG, - "After freeing txq[%d] used and unused buf", i); - VIRTQUEUE_DUMP(txvq->vq); + "After freeing %s[%d] used and unused buf", + type, i); + VIRTQUEUE_DUMP(vq); } + + PMD_INIT_LOG(DEBUG, "%d mbufs freed", mbuf_num); } /* @@ -1841,27 +2262,41 @@ virtio_dev_stop(struct rte_eth_dev *dev) PMD_INIT_LOG(DEBUG, "stop"); - if (intr_conf->lsc || intr_conf->rxq) - rte_intr_disable(dev->intr_handle); + rte_spinlock_lock(&hw->state_lock); + if (!hw->started) + goto out_unlock; + hw->started = false; + + if (intr_conf->lsc || intr_conf->rxq) { + virtio_intr_disable(dev); + + /* Reset interrupt callback */ + if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) { + rte_intr_callback_unregister(dev->intr_handle, + virtio_interrupt_handler, + dev); + } + } - hw->started = 0; memset(&link, 0, sizeof(link)); - virtio_dev_atomic_write_link_status(dev, &link); + rte_eth_linkstatus_set(dev, &link); +out_unlock: + rte_spinlock_unlock(&hw->state_lock); } static int virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complete) { - struct rte_eth_link link, old; + struct rte_eth_link link; uint16_t status; struct virtio_hw *hw = dev->data->dev_private; + memset(&link, 0, sizeof(link)); - virtio_dev_atomic_read_link_status(dev, &link); - old = link; link.link_duplex = ETH_LINK_FULL_DUPLEX; - link.link_speed = SPEED_10G; + link.link_speed = ETH_SPEED_NUM_10G; + link.link_autoneg = ETH_LINK_FIXED; - if (hw->started == 0) { + if (!hw->started) { link.link_status = ETH_LINK_DOWN; } else if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { PMD_INIT_LOG(DEBUG, "Get link status from hw"); @@ -1880,9 +2315,32 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet } else { link.link_status = ETH_LINK_UP; } - virtio_dev_atomic_write_link_status(dev, &link); - return (old.link_status == link.link_status) ? -1 : 0; + return rte_eth_linkstatus_set(dev, &link); +} + +static int +virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask) +{ + const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode; + struct virtio_hw *hw = dev->data->dev_private; + uint64_t offloads = rxmode->offloads; + + if (mask & ETH_VLAN_FILTER_MASK) { + if ((offloads & DEV_RX_OFFLOAD_VLAN_FILTER) && + !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { + + PMD_DRV_LOG(NOTICE, + "vlan filtering not available on this host"); + + return -ENOTSUP; + } + } + + if (mask & ETH_VLAN_STRIP_MASK) + hw->vlan_strip = !!(offloads & DEV_RX_OFFLOAD_VLAN_STRIP); + + return 0; } static void @@ -1893,7 +2351,6 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */ - dev_info->pci_dev = dev->device ? RTE_ETH_DEV_TO_PCI(dev) : NULL; dev_info->max_rx_queues = RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES); dev_info->max_tx_queues = @@ -1901,31 +2358,32 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) dev_info->min_rx_bufsize = VIRTIO_MIN_RX_BUFSIZE; dev_info->max_rx_pktlen = VIRTIO_MAX_RX_PKTLEN; dev_info->max_mac_addrs = VIRTIO_MAX_MAC_ADDRS; - dev_info->default_txconf = (struct rte_eth_txconf) { - .txq_flags = ETH_TXQ_FLAGS_NOOFFLOADS - }; host_features = VTPCI_OPS(hw)->get_features(hw); - dev_info->rx_offload_capa = 0; + dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP; + dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_JUMBO_FRAME; if (host_features & (1ULL << VIRTIO_NET_F_GUEST_CSUM)) { dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_CKSUM | DEV_RX_OFFLOAD_UDP_CKSUM; } + if (host_features & (1ULL << VIRTIO_NET_F_CTRL_VLAN)) + dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_VLAN_FILTER; tso_mask = (1ULL << VIRTIO_NET_F_GUEST_TSO4) | (1ULL << VIRTIO_NET_F_GUEST_TSO6); if ((host_features & tso_mask) == tso_mask) dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_TCP_LRO; - dev_info->tx_offload_capa = 0; - if (hw->guest_features & (1ULL << VIRTIO_NET_F_CSUM)) { + dev_info->tx_offload_capa = DEV_TX_OFFLOAD_MULTI_SEGS | + DEV_TX_OFFLOAD_VLAN_INSERT; + if (host_features & (1ULL << VIRTIO_NET_F_CSUM)) { dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_UDP_CKSUM | DEV_TX_OFFLOAD_TCP_CKSUM; } tso_mask = (1ULL << VIRTIO_NET_F_HOST_TSO4) | (1ULL << VIRTIO_NET_F_HOST_TSO6); - if ((hw->guest_features & tso_mask) == tso_mask) + if ((host_features & tso_mask) == tso_mask) dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO; } @@ -1943,3 +2401,13 @@ __rte_unused uint8_t is_rx) RTE_PMD_EXPORT_NAME(net_virtio, __COUNTER__); RTE_PMD_REGISTER_PCI_TABLE(net_virtio, pci_id_virtio_map); RTE_PMD_REGISTER_KMOD_DEP(net_virtio, "* igb_uio | uio_pci_generic | vfio-pci"); + +RTE_INIT(virtio_init_log) +{ + virtio_logtype_init = rte_log_register("pmd.net.virtio.init"); + if (virtio_logtype_init >= 0) + rte_log_set_level(virtio_logtype_init, RTE_LOG_NOTICE); + virtio_logtype_driver = rte_log_register("pmd.net.virtio.driver"); + if (virtio_logtype_driver >= 0) + rte_log_set_level(virtio_logtype_driver, RTE_LOG_NOTICE); +}