X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=ee5a98b7c073bba636c9fa96fdf28144b7410742;hb=239810607333f7e68979781b0c7be2a14c242f6a;hp=730c41707d3314801d172d4d5a07c3a356f3bdfa;hpb=8f62ec38616b16491f8601fc54ad5d643ef0e339;p=dpdk.git diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c index 730c41707d..ee5a98b7c0 100644 --- a/drivers/net/virtio/virtio_ethdev.c +++ b/drivers/net/virtio/virtio_ethdev.c @@ -141,6 +141,97 @@ static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = { struct virtio_hw_internal virtio_hw_internal[RTE_MAX_ETHPORTS]; +static struct virtio_pmd_ctrl * +virtio_pq_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, + int *dlen, int pkt_num) +{ + struct virtqueue *vq = cvq->vq; + int head; + struct vring_packed_desc *desc = vq->ring_packed.desc_packed; + struct virtio_pmd_ctrl *result; + bool avail_wrap_counter, used_wrap_counter; + uint16_t flags; + int sum = 0; + int k; + + /* + * 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; + avail_wrap_counter = vq->avail_wrap_counter; + used_wrap_counter = vq->used_wrap_counter; + desc[head].flags = VRING_DESC_F_NEXT; + desc[head].addr = cvq->virtio_net_hdr_mem; + desc[head].len = sizeof(struct virtio_net_ctrl_hdr); + vq->vq_free_cnt--; + if (++vq->vq_avail_idx >= vq->vq_nentries) { + vq->vq_avail_idx -= vq->vq_nentries; + vq->avail_wrap_counter ^= 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]; + flags = VRING_DESC_F_NEXT; + sum += dlen[k]; + vq->vq_free_cnt--; + flags |= VRING_DESC_F_AVAIL(vq->avail_wrap_counter) | + VRING_DESC_F_USED(!vq->avail_wrap_counter); + desc[vq->vq_avail_idx].flags = flags; + rte_smp_wmb(); + vq->vq_free_cnt--; + if (++vq->vq_avail_idx >= vq->vq_nentries) { + vq->vq_avail_idx -= vq->vq_nentries; + vq->avail_wrap_counter ^= 1; + } + } + + + 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); + flags = VRING_DESC_F_WRITE; + flags |= VRING_DESC_F_AVAIL(vq->avail_wrap_counter) | + VRING_DESC_F_USED(!vq->avail_wrap_counter); + desc[vq->vq_avail_idx].flags = flags; + flags = VRING_DESC_F_NEXT; + flags |= VRING_DESC_F_AVAIL(avail_wrap_counter) | + VRING_DESC_F_USED(!avail_wrap_counter); + desc[head].flags = flags; + rte_smp_wmb(); + + vq->vq_free_cnt--; + if (++vq->vq_avail_idx >= vq->vq_nentries) { + vq->vq_avail_idx -= vq->vq_nentries; + vq->avail_wrap_counter ^= 1; + } + + virtqueue_notify(vq); + + /* wait for used descriptors in virtqueue */ + do { + rte_rmb(); + usleep(100); + } while (!__desc_is_used(&desc[head], used_wrap_counter)); + + /* now get used descriptors */ + while (desc_is_used(&desc[vq->vq_used_cons_idx], vq)) { + vq->vq_free_cnt++; + if (++vq->vq_used_cons_idx >= vq->vq_nentries) { + vq->vq_used_cons_idx -= vq->vq_nentries; + vq->used_wrap_counter ^= 1; + } + } + + result = cvq->virtio_net_hdr_mz->addr; + return result; +} + static int virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, int *dlen, int pkt_num) @@ -174,6 +265,11 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, memcpy(cvq->virtio_net_hdr_mz->addr, ctrl, sizeof(struct virtio_pmd_ctrl)); + if (vtpci_packed_queue(vq->hw)) { + result = virtio_pq_send_command(cvq, ctrl, dlen, pkt_num); + goto out_unlock; + } + /* * Format is enforced in qemu code: * One TX packet for header; @@ -245,6 +341,7 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, result = cvq->virtio_net_hdr_mz->addr; +out_unlock: rte_spinlock_unlock(&cvq->lock); return result->status; } @@ -299,20 +396,22 @@ virtio_init_vring(struct virtqueue *vq) 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); - - vring_desc_init(vr->desc, size); - + if (vtpci_packed_queue(vq->hw)) { + vring_init_packed(&vq->ring_packed, ring_mem, + VIRTIO_PCI_VRING_ALIGN, size); + vring_desc_init_packed(vq, size); + } else { + vring_init_split(vr, ring_mem, VIRTIO_PCI_VRING_ALIGN, size); + vring_desc_init_split(vr->desc, size); + } /* * Disable device(host) interrupting guest */ @@ -335,8 +434,10 @@ 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 @@ -372,7 +473,7 @@ 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; @@ -382,17 +483,25 @@ 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; + vq->event_flags_shadow = 0; + if (vtpci_packed_queue(hw)) { + vq->avail_wrap_counter = 1; + vq->used_wrap_counter = 1; + vq->avail_used_flags = + VRING_DESC_F_AVAIL(vq->avail_wrap_counter) | + VRING_DESC_F_USED(!vq->avail_wrap_counter); + } /* * 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, RTE_MEMZONE_IOVA_CONTIG, + numa_node, RTE_MEMZONE_IOVA_CONTIG, VIRTIO_PCI_VRING_ALIGN); if (mz == NULL) { if (rte_errno == EEXIST) @@ -418,7 +527,7 @@ 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, RTE_MEMZONE_IOVA_CONTIG, + numa_node, RTE_MEMZONE_IOVA_CONTIG, RTE_CACHE_LINE_SIZE); if (hdr_mz == NULL) { if (rte_errno == EEXIST) @@ -435,7 +544,7 @@ 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; @@ -488,16 +597,26 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) memset(txr, 0, vq_size * sizeof(*txr)); 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)); + struct vring_packed_desc *start_dp_packed = + txr[i].tx_indir_pq; /* 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)) { + start_dp_packed->addr = txvq->virtio_net_hdr_mem + + i * sizeof(*txr) + + offsetof(struct virtio_tx_region, + tx_hdr); + start_dp_packed->len = hw->vtnet_hdr_size; + } else { + 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; + } } } @@ -588,6 +707,10 @@ 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); @@ -1288,6 +1411,7 @@ 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); @@ -1301,12 +1425,17 @@ virtio_interrupt_handler(void *param) _rte_eth_dev_callback_process(dev, RTE_ETH_EVENT_INTR_LSC, NULL); - } - if (isr & VIRTIO_NET_S_ANNOUNCE) { - virtio_notify_peers(dev); - if (hw->cvq) - virtio_ack_link_announce(dev); + 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); + } + } } } @@ -1316,35 +1445,58 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev) { struct virtio_hw *hw = eth_dev->data->dev_private; - 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 mergeable buffer Rx path on port %u", - eth_dev->data->port_id); - eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts_inorder; - } else if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + if (vtpci_packed_queue(hw)) { PMD_INIT_LOG(INFO, - "virtio: using mergeable buffer Rx path on port %u", + "virtio: using packed ring standard Tx path on port %u", eth_dev->data->port_id); - eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts; + eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed; } 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; + 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 (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; + 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 { - 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 (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. @@ -1462,6 +1614,8 @@ 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); @@ -1476,7 +1630,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) /* 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); @@ -1679,11 +1834,6 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) if (ret < 0) goto out; - /* 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); - return 0; out: @@ -1706,14 +1856,6 @@ 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)); @@ -1763,6 +1905,11 @@ exit: 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; @@ -1788,11 +1935,7 @@ static struct rte_pci_driver rte_virtio_pmd = { 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); } @@ -1908,12 +2051,14 @@ virtio_dev_configure(struct rte_eth_dev *dev) if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) { hw->use_inorder_tx = 1; - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { - hw->use_inorder_rx = 1; - hw->use_simple_rx = 0; - } else { - hw->use_inorder_rx = 0; - } + 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; + hw->use_inorder_tx = 0; } #if defined RTE_ARCH_ARM64 || defined RTE_ARCH_ARM @@ -1931,6 +2076,8 @@ virtio_dev_configure(struct rte_eth_dev *dev) DEV_RX_OFFLOAD_VLAN_STRIP)) hw->use_simple_rx = 0; + hw->opened = true; + return 0; } @@ -1972,6 +2119,12 @@ virtio_dev_start(struct rte_eth_dev *dev) dev->data->dev_conf.intr_conf.rxq) { virtio_intr_disable(dev); + /* 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; @@ -2015,7 +2168,7 @@ virtio_dev_start(struct rte_eth_dev *dev) } set_rxtx_funcs(dev); - hw->started = 1; + hw->started = true; /* Initialize Link state */ virtio_dev_link_update(dev, 0); @@ -2081,12 +2234,24 @@ virtio_dev_stop(struct rte_eth_dev *dev) PMD_INIT_LOG(DEBUG, "stop"); rte_spinlock_lock(&hw->state_lock); - if (intr_conf->lsc || intr_conf->rxq) + if (!hw->started) + goto out_unlock; + hw->started = false; + + if (intr_conf->lsc || intr_conf->rxq) { virtio_intr_disable(dev); - hw->started = 0; + /* Reset interrupt callback */ + if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) { + rte_intr_callback_unregister(dev->intr_handle, + virtio_interrupt_handler, + dev); + } + } + memset(&link, 0, sizeof(link)); rte_eth_linkstatus_set(dev, &link); +out_unlock: rte_spinlock_unlock(&hw->state_lock); } @@ -2102,7 +2267,7 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet 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");