X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fvirtio%2Fvirtio_ethdev.c;h=090d94615e9c45fef57db3f0f108a712ab2e1ed5;hb=da573c0e4205d818cd602eaa27c720896f3b6f1c;hp=9060b6b33a370ce6110569b4afd6611858b3d772;hpb=8e148e492022f9e0a8bf1c48e59a199c86ccc65b;p=dpdk.git diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c index 9060b6b33a..090d94615e 100644 --- a/drivers/net/virtio/virtio_ethdev.c +++ b/drivers/net/virtio/virtio_ethdev.c @@ -8,43 +8,44 @@ #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 #include "virtio_ethdev.h" -#include "virtio_pci.h" +#include "virtio.h" #include "virtio_logs.h" #include "virtqueue.h" #include "virtio_rxtx.h" +#include "virtio_user/virtio_user_dev.h" -static int eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev); static int virtio_dev_configure(struct rte_eth_dev *dev); static int virtio_dev_start(struct rte_eth_dev *dev); -static void virtio_dev_stop(struct rte_eth_dev *dev); -static void virtio_dev_promiscuous_enable(struct rte_eth_dev *dev); -static void virtio_dev_promiscuous_disable(struct rte_eth_dev *dev); -static void virtio_dev_allmulticast_enable(struct rte_eth_dev *dev); -static void virtio_dev_allmulticast_disable(struct rte_eth_dev *dev); -static void virtio_dev_info_get(struct rte_eth_dev *dev, +static int virtio_dev_promiscuous_enable(struct rte_eth_dev *dev); +static int virtio_dev_promiscuous_disable(struct rte_eth_dev *dev); +static int virtio_dev_allmulticast_enable(struct rte_eth_dev *dev); +static int virtio_dev_allmulticast_disable(struct rte_eth_dev *dev); +static uint32_t virtio_dev_speed_capa_get(uint32_t speed); +static int virtio_dev_devargs_parse(struct rte_devargs *devargs, + uint32_t *speed, + int *vectorized); +static int 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); @@ -60,16 +61,16 @@ static int virtio_dev_xstats_get(struct rte_eth_dev *dev, static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev, struct rte_eth_xstat_name *xstats_names, unsigned limit); -static void virtio_dev_stats_reset(struct rte_eth_dev *dev); +static int virtio_dev_stats_reset(struct rte_eth_dev *dev); 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 int virtio_mac_addr_set(struct rte_eth_dev *dev, - struct ether_addr *mac_addr); + struct rte_ether_addr *mac_addr); static int virtio_intr_disable(struct rte_eth_dev *dev); @@ -79,21 +80,9 @@ 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 - */ -static const struct rte_pci_id pci_id_virtio_map[] = { - { RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_LEGACY_DEVICEID_NET) }, - { RTE_PCI_DEVICE(VIRTIO_PCI_VENDORID, VIRTIO_PCI_MODERN_DEVICEID_NET) }, - { .vendor_id = 0, /* sentinel */ }, -}; - struct rte_virtio_xstats_name_off { char name[RTE_ETH_XSTATS_NAME_SIZE]; unsigned offset; @@ -120,7 +109,6 @@ static const struct rte_virtio_xstats_name_off rte_virtio_rxq_stat_strings[] = { static const struct rte_virtio_xstats_name_off rte_virtio_txq_stat_strings[] = { {"good_packets", offsetof(struct virtnet_tx, stats.packets)}, {"good_bytes", offsetof(struct virtnet_tx, stats.bytes)}, - {"errors", offsetof(struct virtnet_tx, stats.errors)}, {"multicast_packets", offsetof(struct virtnet_tx, stats.multicast)}, {"broadcast_packets", offsetof(struct virtnet_tx, stats.broadcast)}, {"undersize_packets", offsetof(struct virtnet_tx, stats.size_bins[0])}, @@ -145,9 +133,9 @@ virtio_send_command_packed(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, int *dlen, int pkt_num) { - struct virtqueue *vq = cvq->vq; + struct virtqueue *vq = virtnet_cq_to_vq(cvq); int head; - struct vring_packed_desc *desc = vq->ring_packed.desc_packed; + struct vring_packed_desc *desc = vq->vq_packed.ring.desc; struct virtio_pmd_ctrl *result; uint16_t flags; int sum = 0; @@ -161,15 +149,14 @@ virtio_send_command_packed(struct virtnet_ctl *cvq, * One RX packet for ACK. */ head = vq->vq_avail_idx; - flags = vq->cached_flags; + 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->cached_flags ^= - VRING_DESC_F_AVAIL(1) | VRING_DESC_F_USED(1); + vq->vq_packed.cached_flags ^= VRING_PACKED_DESC_F_AVAIL_USED; } for (k = 0; k < pkt_num; k++) { @@ -178,132 +165,106 @@ virtio_send_command_packed(struct virtnet_ctl *cvq, + 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->cached_flags; + 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->cached_flags ^= - VRING_DESC_F_AVAIL(1) | VRING_DESC_F_USED(1); + vq->vq_packed.cached_flags ^= + VRING_PACKED_DESC_F_AVAIL_USED; } } 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->cached_flags; + 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->cached_flags ^= - VRING_DESC_F_AVAIL(1) | VRING_DESC_F_USED(1); + vq->vq_packed.cached_flags ^= VRING_PACKED_DESC_F_AVAIL_USED; } - virtio_wmb(vq->hw->weak_barriers); - desc[head].flags = VRING_DESC_F_NEXT | flags; + virtqueue_store_flags_packed(&desc[head], VRING_DESC_F_NEXT | flags, + vq->hw->weak_barriers); virtio_wmb(vq->hw->weak_barriers); virtqueue_notify(vq); - /* wait for used descriptors in virtqueue */ + /* wait for used desc in virtqueue + * desc_is_used has a load-acquire or rte_io_rmb inside + */ 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->used_wrap_counter ^= 1; + 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->cached_flags=0x%x\n" - "vq->used_wrap_counter=%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->cached_flags, - vq->used_wrap_counter); + vq->vq_packed.cached_flags, + vq->vq_packed.used_wrap_counter); 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) +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 = virtnet_cq_to_vq(cvq); uint32_t head, i; int k, sum = 0; - 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; 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); - - 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); - goto out_unlock; - } - /* * Format is enforced in qemu code: * One TX packet for header; * 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); @@ -312,28 +273,26 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, virtqueue_notify(vq); - rte_rmb(); - while (VIRTQUEUE_NUSED(vq) == 0) { - rte_rmb(); + while (virtqueue_nused(vq) == 0) usleep(100); - } - while (VIRTQUEUE_NUSED(vq)) { + while (virtqueue_nused(vq)) { uint32_t idx, desc_idx, used_idx; struct vring_used_elem *uep; 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++; @@ -344,8 +303,44 @@ virtio_send_command(struct virtnet_ctl *cvq, struct virtio_pmd_ctrl *ctrl, vq->vq_free_cnt, vq->vq_desc_head_idx); 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) +{ + virtio_net_ctrl_ack status = ~0; + struct virtio_pmd_ctrl *result; + struct virtqueue *vq; + + ctrl->status = status; + + if (!cvq) { + PMD_INIT_LOG(ERR, "Control queue is not supported."); + return -1; + } + + rte_spinlock_lock(&cvq->lock); + vq = virtnet_cq_to_vq(cvq); + + 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 (virtio_with_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); -out_unlock: rte_spinlock_unlock(&cvq->lock); return result->status; } @@ -385,7 +380,7 @@ virtio_get_nr_vq(struct virtio_hw *hw) { uint16_t nr_vq = hw->max_queue_pairs * 2; - if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) + if (virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) nr_vq += 1; return nr_vq; @@ -395,7 +390,6 @@ 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(); @@ -408,12 +402,14 @@ virtio_init_vring(struct virtqueue *vq) 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->ring_packed, ring_mem, - VIRTIO_PCI_VRING_ALIGN, size); + if (virtio_with_packed_queue(vq->hw)) { + vring_init_packed(&vq->vq_packed.ring, ring_mem, + VIRTIO_VRING_ALIGN, size); vring_desc_init_packed(vq, size); } else { - vring_init_split(vr, ring_mem, VIRTIO_PCI_VRING_ALIGN, size); + struct vring *vr = &vq->vq_split.ring; + + vring_init_split(vr, ring_mem, VIRTIO_VRING_ALIGN, size); vring_desc_init_split(vr->desc, size); } /* @@ -423,7 +419,7 @@ virtio_init_vring(struct virtqueue *vq) } static int -virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) +virtio_init_queue(struct rte_eth_dev *dev, uint16_t queue_idx) { char vq_name[VIRTQUEUE_MAX_NAME_SZ]; char vq_hdr_name[VIRTQUEUE_MAX_NAME_SZ]; @@ -436,31 +432,32 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) struct virtqueue *vq; size_t sz_hdr_mz = 0; void *sw_ring = NULL; - int queue_type = virtio_get_queue_type(hw, vtpci_queue_idx); + int queue_type = virtio_get_queue_type(hw, queue_idx); int ret; int numa_node = dev->device->numa_node; + struct rte_mbuf *fake_mbuf = NULL; PMD_INIT_LOG(INFO, "setting up queue: %u on NUMA node %d", - vtpci_queue_idx, numa_node); + queue_idx, numa_node); /* * Read the virtqueue size from the Queue Size field * Always power of 2 and if 0 virtqueue does not exist */ - vq_size = VTPCI_OPS(hw)->get_queue_num(hw, vtpci_queue_idx); + vq_size = VIRTIO_OPS(hw)->get_queue_num(hw, queue_idx); PMD_INIT_LOG(DEBUG, "vq_size: %u", vq_size); if (vq_size == 0) { PMD_INIT_LOG(ERR, "virtqueue does not exist"); return -EINVAL; } - if (!rte_is_power_of_2(vq_size)) { - PMD_INIT_LOG(ERR, "virtqueue size is not powerof 2"); + if (!virtio_with_packed_queue(hw) && !rte_is_power_of_2(vq_size)) { + PMD_INIT_LOG(ERR, "split virtqueue size is not power of 2"); return -EINVAL; } snprintf(vq_name, sizeof(vq_name), "port%d_vq%d", - dev->data->port_id, vtpci_queue_idx); + dev->data->port_id, queue_idx); size = RTE_ALIGN_CEIL(sizeof(*vq) + vq_size * sizeof(struct vq_desc_extra), @@ -473,7 +470,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) sz_hdr_mz = vq_size * sizeof(struct virtio_tx_region); } else if (queue_type == VTNET_CQ) { /* Allocate a page for control vq command, data and status */ - sz_hdr_mz = PAGE_SIZE; + sz_hdr_mz = rte_mem_page_size(); } vq = rte_zmalloc_socket(vq_name, size, RTE_CACHE_LINE_SIZE, @@ -482,36 +479,36 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) PMD_INIT_LOG(ERR, "can not allocate vq"); return -ENOMEM; } - hw->vqs[vtpci_queue_idx] = vq; + hw->vqs[queue_idx] = vq; vq->hw = hw; - vq->vq_queue_index = vtpci_queue_idx; + vq->vq_queue_index = queue_idx; vq->vq_nentries = vq_size; - vq->event_flags_shadow = 0; - if (vtpci_packed_queue(hw)) { - vq->used_wrap_counter = 1; - vq->cached_flags = VRING_DESC_F_AVAIL(1); + if (virtio_with_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->cached_flags |= VRING_DESC_F_WRITE; + vq->vq_packed.cached_flags |= VRING_DESC_F_WRITE; } /* * Reserve a memzone for vring elements */ - size = vring_size(hw, vq_size, VIRTIO_PCI_VRING_ALIGN); - vq->vq_ring_size = RTE_ALIGN_CEIL(size, VIRTIO_PCI_VRING_ALIGN); + size = vring_size(hw, vq_size, VIRTIO_VRING_ALIGN); + vq->vq_ring_size = RTE_ALIGN_CEIL(size, VIRTIO_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, numa_node, RTE_MEMZONE_IOVA_CONTIG, - VIRTIO_PCI_VRING_ALIGN); + VIRTIO_VRING_ALIGN); if (mz == NULL) { if (rte_errno == EEXIST) mz = rte_memzone_lookup(vq_name); if (mz == NULL) { ret = -ENOMEM; - goto fail_q_alloc; + goto free_vq; } } @@ -528,7 +525,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) if (sz_hdr_mz) { snprintf(vq_hdr_name, sizeof(vq_hdr_name), "port%d_vq%d_hdr", - dev->data->port_id, vtpci_queue_idx); + dev->data->port_id, queue_idx); hdr_mz = rte_memzone_reserve_aligned(vq_hdr_name, sz_hdr_mz, numa_node, RTE_MEMZONE_IOVA_CONTIG, RTE_CACHE_LINE_SIZE); @@ -537,7 +534,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) hdr_mz = rte_memzone_lookup(vq_hdr_name); if (hdr_mz == NULL) { ret = -ENOMEM; - goto fail_q_alloc; + goto free_mz; } } } @@ -551,47 +548,38 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) if (!sw_ring) { PMD_INIT_LOG(ERR, "can not allocate RX soft ring"); ret = -ENOMEM; - goto fail_q_alloc; + goto free_hdr_mz; + } + + fake_mbuf = rte_zmalloc_socket("sw_ring", sizeof(*fake_mbuf), + RTE_CACHE_LINE_SIZE, numa_node); + if (!fake_mbuf) { + PMD_INIT_LOG(ERR, "can not allocate fake mbuf"); + ret = -ENOMEM; + goto free_sw_ring; } vq->sw_ring = sw_ring; rxvq = &vq->rxq; - rxvq->vq = vq; rxvq->port_id = dev->data->port_id; rxvq->mz = mz; + rxvq->fake_mbuf = fake_mbuf; } else if (queue_type == VTNET_TQ) { txvq = &vq->txq; - txvq->vq = vq; txvq->port_id = dev->data->port_id; txvq->mz = mz; txvq->virtio_net_hdr_mz = hdr_mz; 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->iova; - memset(cvq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE); + memset(cvq->virtio_net_hdr_mz->addr, 0, rte_mem_page_size()); hw->cvq = cvq; } - /* For virtio_user case (that is when hw->dev is NULL), we use - * virtual address. And we need properly set _offset_, please see - * VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information. - */ - if (!hw->virtio_user_dev) - 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); - if (queue_type == VTNET_TQ) - txvq->virtio_net_hdr_mem = (uintptr_t)hdr_mz->addr; - else if (queue_type == VTNET_CQ) - cvq->virtio_net_hdr_mem = (uintptr_t)hdr_mz->addr; - } - if (queue_type == VTNET_TQ) { struct virtio_tx_region *txr; unsigned int i; @@ -599,41 +587,49 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx) txr = hdr_mz->addr; memset(txr, 0, vq_size * sizeof(*txr)); for (i = 0; i < vq_size; i++) { - struct vring_desc *start_dp = txr[i].tx_indir; - struct vring_packed_desc *start_dp_packed = - txr[i].tx_indir_pq; - /* first indirect descriptor is always the tx header */ - if (vtpci_packed_queue(hw)) { - start_dp_packed->addr = txvq->virtio_net_hdr_mem + if (!virtio_with_packed_queue(hw)) { + struct vring_desc *start_dp = txr[i].tx_indir; + 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_packed->len = hw->vtnet_hdr_size; + start_dp->len = hw->vtnet_hdr_size; + start_dp->flags = VRING_DESC_F_NEXT; } else { - vring_desc_init_split(start_dp, - RTE_DIM(txr[i].tx_indir)); + struct vring_packed_desc *start_dp = + txr[i].tx_packed_indir; + vring_desc_init_indirect_packed(start_dp, + RTE_DIM(txr[i].tx_packed_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; } } } - if (VTPCI_OPS(hw)->setup_queue(hw, vq) < 0) { + if (VIRTIO_OPS(hw)->setup_queue(hw, vq) < 0) { PMD_INIT_LOG(ERR, "setup_queue failed"); - return -EINVAL; + ret = -EINVAL; + goto clean_vq; } return 0; -fail_q_alloc: +clean_vq: + hw->cvq = NULL; + rte_free(fake_mbuf); +free_sw_ring: rte_free(sw_ring); +free_hdr_mz: rte_memzone_free(hdr_mz); +free_mz: rte_memzone_free(mz); +free_vq: rte_free(vq); return ret; @@ -657,6 +653,7 @@ virtio_free_queues(struct virtio_hw *hw) queue_type = virtio_get_queue_type(hw, i); if (queue_type == VTNET_RQ) { + rte_free(vq->rxq.fake_mbuf); rte_free(vq->sw_ring); rte_memzone_free(vq->rxq.mz); } else if (queue_type == VTNET_TQ) { @@ -702,21 +699,23 @@ virtio_alloc_queues(struct rte_eth_dev *dev) static void virtio_queues_unbind_intr(struct rte_eth_dev *dev); -static void +int virtio_dev_close(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; struct rte_intr_conf *intr_conf = &dev->data->dev_conf.intr_conf; PMD_INIT_LOG(DEBUG, "virtio_dev_close"); + if (rte_eal_process_type() != RTE_PROC_PRIMARY) + return 0; if (!hw->opened) - return; - hw->opened = false; + return 0; + hw->opened = 0; /* reset the NIC */ if (dev->data->dev_flags & RTE_ETH_DEV_INTR_LSC) - VTPCI_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR); + VIRTIO_OPS(hw)->set_config_irq(hw, VIRTIO_MSI_NO_VECTOR); if (intr_conf->rxq) virtio_queues_unbind_intr(dev); @@ -727,12 +726,14 @@ virtio_dev_close(struct rte_eth_dev *dev) dev->intr_handle->intr_vec = NULL; } - vtpci_reset(hw); + virtio_reset(hw); virtio_dev_free_mbufs(dev); virtio_free_queues(hw); + + return VIRTIO_OPS(hw)->dev_close(hw); } -static void +static int virtio_dev_promiscuous_enable(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; @@ -740,9 +741,9 @@ virtio_dev_promiscuous_enable(struct rte_eth_dev *dev) int dlen[1]; int ret; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { PMD_INIT_LOG(INFO, "host does not support rx control"); - return; + return -ENOTSUP; } ctrl.hdr.class = VIRTIO_NET_CTRL_RX; @@ -751,11 +752,15 @@ virtio_dev_promiscuous_enable(struct rte_eth_dev *dev) dlen[0] = 1; ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1); - if (ret) + if (ret) { PMD_INIT_LOG(ERR, "Failed to enable promisc"); + return -EAGAIN; + } + + return 0; } -static void +static int virtio_dev_promiscuous_disable(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; @@ -763,9 +768,9 @@ virtio_dev_promiscuous_disable(struct rte_eth_dev *dev) int dlen[1]; int ret; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { PMD_INIT_LOG(INFO, "host does not support rx control"); - return; + return -ENOTSUP; } ctrl.hdr.class = VIRTIO_NET_CTRL_RX; @@ -774,11 +779,15 @@ virtio_dev_promiscuous_disable(struct rte_eth_dev *dev) dlen[0] = 1; ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1); - if (ret) + if (ret) { PMD_INIT_LOG(ERR, "Failed to disable promisc"); + return -EAGAIN; + } + + return 0; } -static void +static int virtio_dev_allmulticast_enable(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; @@ -786,9 +795,9 @@ virtio_dev_allmulticast_enable(struct rte_eth_dev *dev) int dlen[1]; int ret; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { PMD_INIT_LOG(INFO, "host does not support rx control"); - return; + return -ENOTSUP; } ctrl.hdr.class = VIRTIO_NET_CTRL_RX; @@ -797,11 +806,15 @@ virtio_dev_allmulticast_enable(struct rte_eth_dev *dev) dlen[0] = 1; ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1); - if (ret) + if (ret) { PMD_INIT_LOG(ERR, "Failed to enable allmulticast"); + return -EAGAIN; + } + + return 0; } -static void +static int virtio_dev_allmulticast_disable(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; @@ -809,9 +822,9 @@ virtio_dev_allmulticast_disable(struct rte_eth_dev *dev) int dlen[1]; int ret; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_RX)) { PMD_INIT_LOG(INFO, "host does not support rx control"); - return; + return -ENOTSUP; } ctrl.hdr.class = VIRTIO_NET_CTRL_RX; @@ -820,8 +833,12 @@ virtio_dev_allmulticast_disable(struct rte_eth_dev *dev) dlen[0] = 1; ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1); - if (ret) + if (ret) { PMD_INIT_LOG(ERR, "Failed to disable allmulticast"); + return -EAGAIN; + } + + return 0; } #define VLAN_TAG_LEN 4 /* 802.3ac tag (not DMA'd) */ @@ -829,16 +846,16 @@ static int virtio_mtu_set(struct rte_eth_dev *dev, uint16_t mtu) { struct virtio_hw *hw = dev->data->dev_private; - uint32_t ether_hdr_len = ETHER_HDR_LEN + VLAN_TAG_LEN + + uint32_t ether_hdr_len = RTE_ETHER_HDR_LEN + VLAN_TAG_LEN + hw->vtnet_hdr_size; uint32_t frame_size = mtu + ether_hdr_len; uint32_t max_frame_size = hw->max_mtu + ether_hdr_len; max_frame_size = RTE_MIN(max_frame_size, VIRTIO_MAX_RX_PKTLEN); - if (mtu < ETHER_MIN_MTU || frame_size > max_frame_size) { + if (mtu < RTE_ETHER_MIN_MTU || frame_size > max_frame_size) { PMD_INIT_LOG(ERR, "MTU should be between %d and %d", - ETHER_MIN_MTU, max_frame_size - ether_hdr_len); + RTE_ETHER_MIN_MTU, max_frame_size - ether_hdr_len); return -EINVAL; } return 0; @@ -849,7 +866,7 @@ 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; + struct virtqueue *vq = virtnet_rxq_to_vq(rxvq); virtqueue_enable_intr(vq); virtio_mb(hw->weak_barriers); @@ -860,7 +877,7 @@ static int virtio_dev_rx_queue_intr_disable(struct rte_eth_dev *dev, uint16_t queue_id) { struct virtnet_rx *rxvq = dev->data->rx_queues[queue_id]; - struct virtqueue *vq = rxvq->vq; + struct virtqueue *vq = virtnet_rxq_to_vq(rxvq); virtqueue_disable_intr(vq); return 0; @@ -891,7 +908,6 @@ static const struct eth_dev_ops virtio_eth_dev_ops = { .rx_queue_intr_enable = virtio_dev_rx_queue_intr_enable, .rx_queue_intr_disable = virtio_dev_rx_queue_intr_disable, .rx_queue_release = virtio_dev_queue_release, - .rx_descriptor_done = virtio_dev_rx_queue_done, .tx_queue_setup = virtio_dev_tx_queue_setup, .tx_queue_release = virtio_dev_queue_release, /* collect stats per queue */ @@ -902,6 +918,21 @@ static const struct eth_dev_ops virtio_eth_dev_ops = { .mac_addr_set = virtio_mac_addr_set, }; +/* + * dev_ops for virtio-user in secondary processes, as we just have + * some limited supports currently. + */ +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) { @@ -914,7 +945,6 @@ virtio_update_stats(struct rte_eth_dev *dev, struct rte_eth_stats *stats) stats->opackets += txvq->stats.packets; stats->obytes += txvq->stats.bytes; - stats->oerrors += txvq->stats.errors; if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) { stats->q_opackets[i] = txvq->stats.packets; @@ -1040,7 +1070,7 @@ virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) return 0; } -static void +static int virtio_dev_stats_reset(struct rte_eth_dev *dev) { unsigned int i; @@ -1052,7 +1082,6 @@ virtio_dev_stats_reset(struct rte_eth_dev *dev) txvq->stats.packets = 0; txvq->stats.bytes = 0; - txvq->stats.errors = 0; txvq->stats.multicast = 0; txvq->stats.broadcast = 0; memset(txvq->stats.size_bins, 0, @@ -1072,25 +1101,27 @@ virtio_dev_stats_reset(struct rte_eth_dev *dev) memset(rxvq->stats.size_bins, 0, sizeof(rxvq->stats.size_bins[0]) * 8); } + + return 0; } static void virtio_set_hwaddr(struct virtio_hw *hw) { - vtpci_write_dev_config(hw, + virtio_write_dev_config(hw, offsetof(struct virtio_net_config, mac), - &hw->mac_addr, ETHER_ADDR_LEN); + &hw->mac_addr, RTE_ETHER_ADDR_LEN); } static void virtio_get_hwaddr(struct virtio_hw *hw) { - if (vtpci_with_feature(hw, VIRTIO_NET_F_MAC)) { - vtpci_read_dev_config(hw, + if (virtio_with_feature(hw, VIRTIO_NET_F_MAC)) { + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, mac), - &hw->mac_addr, ETHER_ADDR_LEN); + &hw->mac_addr, RTE_ETHER_ADDR_LEN); } else { - eth_random_addr(&hw->mac_addr[0]); + rte_eth_random_addr(&hw->mac_addr[0]); virtio_set_hwaddr(hw); } } @@ -1103,7 +1134,7 @@ virtio_mac_table_set(struct virtio_hw *hw, struct virtio_pmd_ctrl ctrl; int err, len[2]; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) { PMD_DRV_LOG(INFO, "host does not support mac table"); return -1; } @@ -1111,10 +1142,10 @@ virtio_mac_table_set(struct virtio_hw *hw, ctrl.hdr.class = VIRTIO_NET_CTRL_MAC; ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_TABLE_SET; - len[0] = uc->entries * ETHER_ADDR_LEN + sizeof(uc->entries); + len[0] = uc->entries * RTE_ETHER_ADDR_LEN + sizeof(uc->entries); memcpy(ctrl.data, uc, len[0]); - len[1] = mc->entries * ETHER_ADDR_LEN + sizeof(mc->entries); + len[1] = mc->entries * RTE_ETHER_ADDR_LEN + sizeof(mc->entries); memcpy(ctrl.data + len[0], mc, len[1]); err = virtio_send_command(hw->cvq, &ctrl, len, 2); @@ -1124,11 +1155,11 @@ 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; @@ -1137,18 +1168,20 @@ virtio_mac_addr_add(struct rte_eth_dev *dev, struct ether_addr *mac_addr, return -EINVAL; } - uc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(uc->entries)); + uc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN + + sizeof(uc->entries)); uc->entries = 0; - mc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(mc->entries)); + mc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN + + sizeof(mc->entries)); 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; + = rte_is_multicast_ether_addr(addr) ? mc : uc; - memcpy(&tbl->macs[tbl->entries++], addr, ETHER_ADDR_LEN); + memcpy(&tbl->macs[tbl->entries++], addr, RTE_ETHER_ADDR_LEN); } return virtio_mac_table_set(hw, uc, mc); @@ -1158,7 +1191,7 @@ 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; @@ -1167,44 +1200,47 @@ virtio_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index) return; } - uc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(uc->entries)); + uc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN + + sizeof(uc->entries)); uc->entries = 0; - mc = alloca(VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN + sizeof(mc->entries)); + mc = alloca(VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN + + sizeof(mc->entries)); mc->entries = 0; for (i = 0; i < VIRTIO_MAX_MAC_ADDRS; i++) { struct virtio_net_ctrl_mac *tbl; - if (i == index || is_zero_ether_addr(addrs + i)) + if (i == index || rte_is_zero_ether_addr(addrs + i)) continue; - tbl = is_multicast_ether_addr(addrs + i) ? mc : uc; - memcpy(&tbl->macs[tbl->entries++], addrs + i, ETHER_ADDR_LEN); + tbl = rte_is_multicast_ether_addr(addrs + i) ? mc : uc; + memcpy(&tbl->macs[tbl->entries++], addrs + i, + RTE_ETHER_ADDR_LEN); } virtio_mac_table_set(hw, uc, mc); } static int -virtio_mac_addr_set(struct rte_eth_dev *dev, struct ether_addr *mac_addr) +virtio_mac_addr_set(struct rte_eth_dev *dev, struct rte_ether_addr *mac_addr) { struct virtio_hw *hw = dev->data->dev_private; - memcpy(hw->mac_addr, mac_addr, ETHER_ADDR_LEN); + memcpy(hw->mac_addr, mac_addr, RTE_ETHER_ADDR_LEN); /* Use atomic update if available */ - if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) { + if (virtio_with_feature(hw, VIRTIO_NET_F_CTRL_MAC_ADDR)) { struct virtio_pmd_ctrl ctrl; - int len = ETHER_ADDR_LEN; + int len = RTE_ETHER_ADDR_LEN; ctrl.hdr.class = VIRTIO_NET_CTRL_MAC; ctrl.hdr.cmd = VIRTIO_NET_CTRL_MAC_ADDR_SET; - memcpy(ctrl.data, mac_addr, ETHER_ADDR_LEN); + memcpy(ctrl.data, mac_addr, RTE_ETHER_ADDR_LEN); return virtio_send_command(hw->cvq, &ctrl, &len, 1); } - if (!vtpci_with_feature(hw, VIRTIO_NET_F_MAC)) + if (!virtio_with_feature(hw, VIRTIO_NET_F_MAC)) return -ENOTSUP; virtio_set_hwaddr(hw); @@ -1218,7 +1254,7 @@ virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) struct virtio_pmd_ctrl ctrl; int len; - if (!vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) + if (!virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) return -ENOTSUP; ctrl.hdr.class = VIRTIO_NET_CTRL_VLAN; @@ -1229,6 +1265,20 @@ 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_unmask(struct rte_eth_dev *dev) +{ + struct virtio_hw *hw = dev->data->dev_private; + + if (rte_intr_ack(dev->intr_handle) < 0) + return -1; + + if (VIRTIO_OPS(hw)->intr_detect) + VIRTIO_OPS(hw)->intr_detect(hw); + + return 0; +} + static int virtio_intr_enable(struct rte_eth_dev *dev) { @@ -1237,8 +1287,8 @@ virtio_intr_enable(struct rte_eth_dev *dev) 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)); + if (VIRTIO_OPS(hw)->intr_detect) + VIRTIO_OPS(hw)->intr_detect(hw); return 0; } @@ -1251,14 +1301,14 @@ virtio_intr_disable(struct rte_eth_dev *dev) 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)); + if (VIRTIO_OPS(hw)->intr_detect) + VIRTIO_OPS(hw)->intr_detect(hw); return 0; } static int -virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) +virtio_ethdev_negotiate_features(struct virtio_hw *hw, uint64_t req_features) { uint64_t host_features; @@ -1267,7 +1317,7 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) req_features); /* Read device(host) feature bits */ - host_features = VTPCI_OPS(hw)->get_features(hw); + host_features = VIRTIO_OPS(hw)->get_features(hw); PMD_INIT_LOG(DEBUG, "host_features before negotiate = %" PRIx64, host_features); @@ -1275,11 +1325,11 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) if (host_features & req_features & (1ULL << VIRTIO_NET_F_MTU)) { struct virtio_net_config config; - vtpci_read_dev_config(hw, + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, mtu), &config.mtu, sizeof(config.mtu)); - if (config.mtu < ETHER_MIN_MTU) + if (config.mtu < RTE_ETHER_MIN_MTU) req_features &= ~(1ULL << VIRTIO_NET_F_MTU); } @@ -1288,20 +1338,18 @@ virtio_negotiate_features(struct virtio_hw *hw, uint64_t req_features) * guest feature bits. */ hw->guest_features = req_features; - hw->guest_features = vtpci_negotiate_features(hw, host_features); + hw->guest_features = virtio_negotiate_features(hw, host_features); PMD_INIT_LOG(DEBUG, "features after negotiate = %" PRIx64, hw->guest_features); - if (hw->modern) { - if (!vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) { - PMD_INIT_LOG(ERR, - "VIRTIO_F_VERSION_1 features is not enabled."); - return -1; - } - vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_FEATURES_OK); - if (!(vtpci_get_status(hw) & VIRTIO_CONFIG_STATUS_FEATURES_OK)) { - PMD_INIT_LOG(ERR, - "failed to set FEATURES_OK status!"); + if (VIRTIO_OPS(hw)->features_ok(hw) < 0) + return -1; + + if (virtio_with_feature(hw, VIRTIO_F_VERSION_1)) { + virtio_set_status(hw, VIRTIO_CONFIG_STATUS_FEATURES_OK); + + if (!(virtio_get_status(hw) & VIRTIO_CONFIG_STATUS_FEATURES_OK)) { + PMD_INIT_LOG(ERR, "Failed to set FEATURES_OK status!"); return -1; } } @@ -1377,7 +1425,7 @@ virtio_notify_peers(struct rte_eth_dev *dev) return; rarp_mbuf = rte_net_make_rarp_packet(rxvq->mpool, - (struct ether_addr *)hw->mac_addr); + (struct rte_ether_addr *)hw->mac_addr); if (rarp_mbuf == NULL) { PMD_DRV_LOG(ERR, "failed to make RARP packet."); return; @@ -1419,20 +1467,20 @@ virtio_interrupt_handler(void *param) uint16_t status; /* Read interrupt status which clears interrupt */ - isr = vtpci_isr(hw); + isr = virtio_get_isr(hw); PMD_DRV_LOG(INFO, "interrupt status = %#x", isr); - if (virtio_intr_enable(dev) < 0) + if (virtio_intr_unmask(dev) < 0) PMD_DRV_LOG(ERR, "interrupt enable failed"); - if (isr & VIRTIO_PCI_ISR_CONFIG) { + if (isr & VIRTIO_ISR_CONFIG) { if (virtio_dev_link_update(dev, 0) == 0) - _rte_eth_dev_callback_process(dev, - RTE_ETH_EVENT_INTR_LSC, - NULL); + rte_eth_dev_callback_process(dev, + RTE_ETH_EVENT_INTR_LSC, + NULL); - if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { - vtpci_read_dev_config(hw, + if (virtio_with_feature(hw, VIRTIO_NET_F_STATUS)) { + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, status), &status, sizeof(status)); if (status & VIRTIO_NET_S_ANNOUNCE) { @@ -1450,12 +1498,16 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev) { struct virtio_hw *hw = eth_dev->data->dev_private; - if (vtpci_packed_queue(hw)) { + eth_dev->tx_pkt_prepare = virtio_xmit_pkts_prepare; + if (virtio_with_packed_queue(hw)) { PMD_INIT_LOG(INFO, "virtio: using packed ring %s Tx path on port %u", - hw->use_inorder_tx ? "inorder" : "standard", + hw->use_vec_tx ? "vectorized" : "standard", eth_dev->data->port_id); - eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed; + if (hw->use_vec_tx) + eth_dev->tx_pkt_burst = virtio_xmit_pkts_packed_vec; + else + 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", @@ -1468,8 +1520,14 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev) } } - if (vtpci_packed_queue(hw)) { - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + if (virtio_with_packed_queue(hw)) { + if (hw->use_vec_rx) { + PMD_INIT_LOG(INFO, + "virtio: using packed ring vectorized Rx path on port %u", + eth_dev->data->port_id); + eth_dev->rx_pkt_burst = + &virtio_recv_pkts_packed_vec; + } else if (virtio_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); @@ -1482,8 +1540,8 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev) 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", + if (hw->use_vec_rx) { + PMD_INIT_LOG(INFO, "virtio: using vectorized 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) { @@ -1491,7 +1549,7 @@ set_rxtx_funcs(struct rte_eth_dev *eth_dev) "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)) { + } else if (virtio_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); @@ -1518,7 +1576,7 @@ virtio_queues_bind_intr(struct rte_eth_dev *dev) PMD_INIT_LOG(INFO, "queue/interrupt binding"); for (i = 0; i < dev->data->nb_rx_queues; ++i) { dev->intr_handle->intr_vec[i] = i + 1; - if (VTPCI_OPS(hw)->set_queue_irq(hw, hw->vqs[i * 2], i + 1) == + if (VIRTIO_OPS(hw)->set_queue_irq(hw, hw->vqs[i * 2], i + 1) == VIRTIO_MSI_NO_VECTOR) { PMD_DRV_LOG(ERR, "failed to set queue vector"); return -EBUSY; @@ -1536,7 +1594,7 @@ virtio_queues_unbind_intr(struct rte_eth_dev *dev) PMD_INIT_LOG(INFO, "queue/interrupt unbinding"); for (i = 0; i < dev->data->nb_rx_queues; ++i) - VTPCI_OPS(hw)->set_queue_irq(hw, + VIRTIO_OPS(hw)->set_queue_irq(hw, hw->vqs[i * VTNET_CQ], VIRTIO_MSI_NO_VECTOR); } @@ -1593,7 +1651,7 @@ virtio_configure_intr(struct rte_eth_dev *dev) return 0; } - +#define DUPLEX_UNKNOWN 0xff /* reset device and renegotiate features if needed */ static int virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) @@ -1601,11 +1659,10 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) struct virtio_hw *hw = eth_dev->data->dev_private; struct virtio_net_config *config; struct virtio_net_config local_config; - struct rte_pci_device *pci_dev = NULL; int ret; /* Reset the device although not necessary at startup */ - vtpci_reset(hw); + virtio_reset(hw); if (hw->vqs) { virtio_dev_free_mbufs(eth_dev); @@ -1613,53 +1670,66 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) } /* Tell the host we've noticed this device. */ - vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_ACK); + virtio_set_status(hw, VIRTIO_CONFIG_STATUS_ACK); /* Tell the host we've known how to drive the device. */ - vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER); - if (virtio_negotiate_features(hw, req_features) < 0) + virtio_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER); + if (virtio_ethdev_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); - } + hw->weak_barriers = !virtio_with_feature(hw, VIRTIO_F_ORDER_PLATFORM); /* 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 != VIRTIO_MSIX_NONE) + if (virtio_with_feature(hw, VIRTIO_NET_F_STATUS) && hw->intr_lsc) eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC; else eth_dev->data->dev_flags &= ~RTE_ETH_DEV_INTR_LSC; + eth_dev->data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS; + /* 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_RING_PACKED)) + if (virtio_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) || + virtio_with_feature(hw, VIRTIO_F_VERSION_1) || + virtio_with_packed_queue(hw)) 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, + rte_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", hw->mac_addr[0], hw->mac_addr[1], hw->mac_addr[2], hw->mac_addr[3], hw->mac_addr[4], hw->mac_addr[5]); - if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) { + if (hw->speed == ETH_SPEED_NUM_UNKNOWN) { + if (virtio_with_feature(hw, VIRTIO_NET_F_SPEED_DUPLEX)) { + config = &local_config; + virtio_read_dev_config(hw, + offsetof(struct virtio_net_config, speed), + &config->speed, sizeof(config->speed)); + virtio_read_dev_config(hw, + offsetof(struct virtio_net_config, duplex), + &config->duplex, sizeof(config->duplex)); + hw->speed = config->speed; + hw->duplex = config->duplex; + } + } + if (hw->duplex == DUPLEX_UNKNOWN) + hw->duplex = ETH_LINK_FULL_DUPLEX; + PMD_INIT_LOG(DEBUG, "link speed = %d, duplex = %d", + hw->speed, hw->duplex); + if (virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) { config = &local_config; - vtpci_read_dev_config(hw, + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, mac), &config->mac, sizeof(config->mac)); - if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { - vtpci_read_dev_config(hw, + if (virtio_with_feature(hw, VIRTIO_NET_F_STATUS)) { + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, status), &config->status, sizeof(config->status)); } else { @@ -1668,8 +1738,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) config->status = 0; } - if (vtpci_with_feature(hw, VIRTIO_NET_F_MQ)) { - vtpci_read_dev_config(hw, + if (virtio_with_feature(hw, VIRTIO_NET_F_MQ)) { + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, max_virtqueue_pairs), &config->max_virtqueue_pairs, sizeof(config->max_virtqueue_pairs)); @@ -1681,8 +1751,8 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) hw->max_queue_pairs = config->max_virtqueue_pairs; - if (vtpci_with_feature(hw, VIRTIO_NET_F_MTU)) { - vtpci_read_dev_config(hw, + if (virtio_with_feature(hw, VIRTIO_NET_F_MTU)) { + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, mtu), &config->mtu, sizeof(config->mtu)); @@ -1692,7 +1762,7 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) * time, but check again in case it has changed since * then, which should not happen. */ - if (config->mtu < ETHER_MIN_MTU) { + if (config->mtu < RTE_ETHER_MIN_MTU) { PMD_INIT_LOG(ERR, "invalid max MTU value (%u)", config->mtu); return -1; @@ -1703,7 +1773,7 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) eth_dev->data->mtu = config->mtu; } else { - hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - ETHER_HDR_LEN - + hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - RTE_ETHER_HDR_LEN - VLAN_TAG_LEN - hw->vtnet_hdr_size; } @@ -1718,7 +1788,7 @@ 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 - + hw->max_mtu = VIRTIO_MAX_RX_PKTLEN - RTE_ETHER_HDR_LEN - VLAN_TAG_LEN - hw->vtnet_hdr_size; } @@ -1729,66 +1799,16 @@ virtio_init_device(struct rte_eth_dev *eth_dev, uint64_t req_features) if (eth_dev->data->dev_conf.intr_conf.rxq) { if (virtio_configure_intr(eth_dev) < 0) { PMD_INIT_LOG(ERR, "failed to configure interrupt"); + virtio_free_queues(hw); return -1; } } - vtpci_reinit_complete(hw); - - if (pci_dev) - PMD_INIT_LOG(DEBUG, "port %d vendorID=0x%x deviceID=0x%x", - eth_dev->data->port_id, pci_dev->id.vendor_id, - pci_dev->id.device_id); - - return 0; -} - -/* - * Remap the PCI device again (IO port map for legacy device and - * memory map for modern device), so that the secondary process - * could have the PCI initiated correctly. - */ -static int -virtio_remap_pci(struct rte_pci_device *pci_dev, struct virtio_hw *hw) -{ - if (hw->modern) { - /* - * We don't have to re-parse the PCI config space, since - * rte_pci_map_device() makes sure the mapped address - * in secondary process would equal to the one mapped in - * the primary process: error will be returned if that - * requirement is not met. - * - * That said, we could simply reuse all cap pointers - * (such as dev_cfg, common_cfg, etc.) parsed from the - * primary process, which is stored in shared memory. - */ - if (rte_pci_map_device(pci_dev)) { - PMD_INIT_LOG(DEBUG, "failed to map pci device!"); - return -1; - } - } else { - if (rte_pci_ioport_map(pci_dev, 0, VTPCI_IO(hw)) < 0) - return -1; - } + virtio_reinit_complete(hw); return 0; } -static void -virtio_set_vtpci_ops(struct virtio_hw *hw) -{ -#ifdef RTE_VIRTIO_USER - if (hw->virtio_user_dev) - VTPCI_OPS(hw) = &virtio_user_ops; - else -#endif - if (hw->modern) - VTPCI_OPS(hw) = &modern_ops; - else - VTPCI_OPS(hw) = &legacy_ops; -} - /* * This function is based on probe() function in virtio_pci.c * It returns 0 on success. @@ -1797,168 +1817,186 @@ int eth_virtio_dev_init(struct rte_eth_dev *eth_dev) { struct virtio_hw *hw = eth_dev->data->dev_private; + uint32_t speed = ETH_SPEED_NUM_UNKNOWN; + int vectorized = 0; int ret; - RTE_BUILD_BUG_ON(RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr_mrg_rxbuf)); + if (sizeof(struct virtio_net_hdr_mrg_rxbuf) > RTE_PKTMBUF_HEADROOM) { + PMD_INIT_LOG(ERR, + "Not sufficient headroom required = %d, avail = %d", + (int)sizeof(struct virtio_net_hdr_mrg_rxbuf), + RTE_PKTMBUF_HEADROOM); + + return -1; + } eth_dev->dev_ops = &virtio_eth_dev_ops; + eth_dev->rx_descriptor_done = virtio_dev_rx_queue_done; if (rte_eal_process_type() == RTE_PROC_SECONDARY) { - if (!hw->virtio_user_dev) { - ret = virtio_remap_pci(RTE_ETH_DEV_TO_PCI(eth_dev), hw); - if (ret) - return ret; - } - - virtio_set_vtpci_ops(hw); set_rxtx_funcs(eth_dev); - return 0; } + ret = virtio_dev_devargs_parse(eth_dev->device->devargs, &speed, &vectorized); + if (ret < 0) + return ret; + hw->speed = speed; + /* Allocate memory for storing MAC addresses */ - eth_dev->data->mac_addrs = rte_zmalloc("virtio", VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN, 0); + eth_dev->data->mac_addrs = rte_zmalloc("virtio", + VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN, 0); if (eth_dev->data->mac_addrs == NULL) { PMD_INIT_LOG(ERR, "Failed to allocate %d bytes needed to store MAC addresses", - VIRTIO_MAX_MAC_ADDRS * ETHER_ADDR_LEN); + VIRTIO_MAX_MAC_ADDRS * RTE_ETHER_ADDR_LEN); return -ENOMEM; } - hw->port_id = eth_dev->data->port_id; - /* For virtio_user case the hw->virtio_user_dev is populated by - * virtio_user_eth_dev_alloc() before eth_virtio_dev_init() is called. - */ - if (!hw->virtio_user_dev) { - ret = vtpci_init(RTE_ETH_DEV_TO_PCI(eth_dev), hw); - if (ret) - goto out; - } + rte_spinlock_init(&hw->state_lock); /* reset device and negotiate default features */ ret = virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES); if (ret < 0) - goto out; + goto err_virtio_init; + + if (vectorized) { + if (!virtio_with_packed_queue(hw)) { + hw->use_vec_rx = 1; + } else { +#if defined(CC_AVX512_SUPPORT) || defined(RTE_ARCH_ARM) + hw->use_vec_rx = 1; + hw->use_vec_tx = 1; +#else + PMD_DRV_LOG(INFO, + "building environment do not support packed ring vectorized"); +#endif + } + } + + hw->opened = 1; return 0; -out: +err_virtio_init: rte_free(eth_dev->data->mac_addrs); + eth_dev->data->mac_addrs = NULL; return ret; } -static int -eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev) +static uint32_t +virtio_dev_speed_capa_get(uint32_t speed) { - PMD_INIT_FUNC_TRACE(); - - if (rte_eal_process_type() == RTE_PROC_SECONDARY) + switch (speed) { + case ETH_SPEED_NUM_10G: + return ETH_LINK_SPEED_10G; + case ETH_SPEED_NUM_20G: + return ETH_LINK_SPEED_20G; + case ETH_SPEED_NUM_25G: + return ETH_LINK_SPEED_25G; + case ETH_SPEED_NUM_40G: + return ETH_LINK_SPEED_40G; + case ETH_SPEED_NUM_50G: + return ETH_LINK_SPEED_50G; + case ETH_SPEED_NUM_56G: + return ETH_LINK_SPEED_56G; + case ETH_SPEED_NUM_100G: + return ETH_LINK_SPEED_100G; + case ETH_SPEED_NUM_200G: + return ETH_LINK_SPEED_200G; + default: return 0; + } +} - virtio_dev_stop(eth_dev); - virtio_dev_close(eth_dev); - - eth_dev->dev_ops = NULL; - eth_dev->tx_pkt_burst = NULL; - eth_dev->rx_pkt_burst = NULL; - - if (eth_dev->device) - rte_pci_unmap_device(RTE_ETH_DEV_TO_PCI(eth_dev)); - - PMD_INIT_LOG(DEBUG, "dev_uninit completed"); +static int vectorized_check_handler(__rte_unused const char *key, + const char *value, void *ret_val) +{ + if (strcmp(value, "1") == 0) + *(int *)ret_val = 1; + else + *(int *)ret_val = 0; return 0; } -static int vdpa_check_handler(__rte_unused const char *key, - const char *value, __rte_unused void *opaque) +#define VIRTIO_ARG_SPEED "speed" +#define VIRTIO_ARG_VECTORIZED "vectorized" + +static int +link_speed_handler(const char *key __rte_unused, + const char *value, void *ret_val) { - if (strcmp(value, "1")) - return -1; + uint32_t val; + if (!value || !ret_val) + return -EINVAL; + val = strtoul(value, NULL, 0); + /* validate input */ + if (virtio_dev_speed_capa_get(val) == 0) + return -EINVAL; + *(uint32_t *)ret_val = val; return 0; } + static int -vdpa_mode_selected(struct rte_devargs *devargs) +virtio_dev_devargs_parse(struct rte_devargs *devargs, uint32_t *speed, int *vectorized) { 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) + if (kvlist == NULL) { + PMD_INIT_LOG(ERR, "error when parsing param"); return 0; + } - if (!rte_kvargs_count(kvlist, key)) - goto exit; + if (speed && rte_kvargs_count(kvlist, VIRTIO_ARG_SPEED) == 1) { + ret = rte_kvargs_process(kvlist, + VIRTIO_ARG_SPEED, + link_speed_handler, speed); + if (ret < 0) { + PMD_INIT_LOG(ERR, "Failed to parse %s", + VIRTIO_ARG_SPEED); + 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; + if (vectorized && + rte_kvargs_count(kvlist, VIRTIO_ARG_VECTORIZED) == 1) { + ret = rte_kvargs_process(kvlist, + VIRTIO_ARG_VECTORIZED, + vectorized_check_handler, vectorized); + if (ret < 0) { + PMD_INIT_LOG(ERR, "Failed to parse %s", + VIRTIO_ARG_VECTORIZED); + 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); -} - -static int eth_virtio_pci_remove(struct rte_pci_device *pci_dev) -{ - return rte_eth_dev_pci_generic_remove(pci_dev, eth_virtio_dev_uninit); -} - -static struct rte_pci_driver rte_virtio_pmd = { - .driver = { - .name = "net_virtio", - }, - .id_table = pci_id_virtio_map, - .drv_flags = 0, - .probe = eth_virtio_pci_probe, - .remove = eth_virtio_pci_remove, -}; - -RTE_INIT(rte_virtio_pmd_init) -{ - rte_eal_iopl_init(); - rte_pci_register(&rte_virtio_pmd); -} - -static bool +static uint8_t 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); + return virtio_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM) || + virtio_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) || + virtio_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6); } -static bool +static uint8_t 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); + return virtio_with_feature(hw, VIRTIO_NET_F_CSUM) || + virtio_with_feature(hw, VIRTIO_NET_F_HOST_TSO4) || + virtio_with_feature(hw, VIRTIO_NET_F_HOST_TSO6); } /* @@ -1971,7 +2009,7 @@ 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 + + uint32_t ether_hdr_len = RTE_ETHER_HDR_LEN + VLAN_TAG_LEN + hw->vtnet_hdr_size; uint64_t rx_offloads = rxmode->offloads; uint64_t tx_offloads = txmode->offloads; @@ -1981,6 +2019,20 @@ virtio_dev_configure(struct rte_eth_dev *dev) PMD_INIT_LOG(DEBUG, "configure"); req_features = VIRTIO_PMD_DEFAULT_GUEST_FEATURES; + if (rxmode->mq_mode != ETH_MQ_RX_NONE) { + PMD_DRV_LOG(ERR, + "Unsupported Rx multi queue mode %d", + rxmode->mq_mode); + return -EINVAL; + } + + if (txmode->mq_mode != ETH_MQ_TX_NONE) { + PMD_DRV_LOG(ERR, + "Unsupported Tx multi queue mode %d", + txmode->mq_mode); + return -EINVAL; + } + if (dev->data->dev_conf.intr_conf.rxq) { ret = virtio_init_device(dev, hw->req_guest_features); if (ret < 0) @@ -2017,29 +2069,29 @@ virtio_dev_configure(struct rte_eth_dev *dev) if ((rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM | DEV_RX_OFFLOAD_TCP_CKSUM)) && - !vtpci_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) { + !virtio_with_feature(hw, VIRTIO_NET_F_GUEST_CSUM)) { PMD_DRV_LOG(ERR, "rx checksum not available on this host"); return -ENOTSUP; } 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_TSO6))) { + (!virtio_with_feature(hw, VIRTIO_NET_F_GUEST_TSO4) || + !virtio_with_feature(hw, VIRTIO_NET_F_GUEST_TSO6))) { PMD_DRV_LOG(ERR, "Large Receive Offload not available on this host"); return -ENOTSUP; } /* start control queue */ - if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) + if (virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) virtio_dev_cq_start(dev); if (rx_offloads & DEV_RX_OFFLOAD_VLAN_STRIP) hw->vlan_strip = 1; - if ((rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER) - && !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { + if ((rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER) && + !virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { PMD_DRV_LOG(ERR, "vlan filtering not available on this host"); return -ENOTSUP; @@ -2050,43 +2102,90 @@ virtio_dev_configure(struct rte_eth_dev *dev) 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) == + if (VIRTIO_OPS(hw)->set_config_irq(hw, 0) == VIRTIO_MSI_NO_VECTOR) { PMD_DRV_LOG(ERR, "failed to set config vector"); return -EBUSY; } - rte_spinlock_init(&hw->state_lock); - - hw->use_simple_rx = 1; + if (virtio_with_packed_queue(hw)) { +#if defined(RTE_ARCH_X86_64) && defined(CC_AVX512_SUPPORT) + if ((hw->use_vec_rx || hw->use_vec_tx) && + (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) || + !virtio_with_feature(hw, VIRTIO_F_IN_ORDER) || + !virtio_with_feature(hw, VIRTIO_F_VERSION_1) || + rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_512)) { + PMD_DRV_LOG(INFO, + "disabled packed ring vectorized path for requirements not met"); + hw->use_vec_rx = 0; + hw->use_vec_tx = 0; + } +#elif defined(RTE_ARCH_ARM) + if ((hw->use_vec_rx || hw->use_vec_tx) && + (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON) || + !virtio_with_feature(hw, VIRTIO_F_IN_ORDER) || + !virtio_with_feature(hw, VIRTIO_F_VERSION_1) || + rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_128)) { + PMD_DRV_LOG(INFO, + "disabled packed ring vectorized path for requirements not met"); + hw->use_vec_rx = 0; + hw->use_vec_tx = 0; + } +#else + hw->use_vec_rx = 0; + hw->use_vec_tx = 0; +#endif - 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 (hw->use_vec_rx) { + if (virtio_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + PMD_DRV_LOG(INFO, + "disabled packed ring vectorized rx for mrg_rxbuf enabled"); + hw->use_vec_rx = 0; + } - if (vtpci_packed_queue(hw)) { - hw->use_simple_rx = 0; - hw->use_inorder_rx = 0; - } + if (rx_offloads & DEV_RX_OFFLOAD_TCP_LRO) { + PMD_DRV_LOG(INFO, + "disabled packed ring vectorized rx for TCP_LRO enabled"); + hw->use_vec_rx = 0; + } + } + } else { + if (virtio_with_feature(hw, VIRTIO_F_IN_ORDER)) { + hw->use_inorder_tx = 1; + hw->use_inorder_rx = 1; + hw->use_vec_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; - } + if (hw->use_vec_rx) { +#if defined RTE_ARCH_ARM + if (!rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON)) { + PMD_DRV_LOG(INFO, + "disabled split ring vectorized path for requirement not met"); + hw->use_vec_rx = 0; + } #endif - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { - hw->use_simple_rx = 0; - } + if (virtio_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + PMD_DRV_LOG(INFO, + "disabled split ring vectorized rx for mrg_rxbuf enabled"); + hw->use_vec_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; + if (rx_offloads & (DEV_RX_OFFLOAD_UDP_CKSUM | + DEV_RX_OFFLOAD_TCP_CKSUM | + DEV_RX_OFFLOAD_TCP_LRO | + DEV_RX_OFFLOAD_VLAN_STRIP)) { + PMD_DRV_LOG(INFO, + "disabled split ring vectorized rx for offloading enabled"); + hw->use_vec_rx = 0; + } - hw->opened = true; + if (rte_vect_get_max_simd_bitwidth() < RTE_VECT_SIMD_128) { + PMD_DRV_LOG(INFO, + "disabled split ring vectorized rx, max SIMD bitwidth too low"); + hw->use_vec_rx = 0; + } + } + } return 0; } @@ -2096,8 +2195,7 @@ static int virtio_dev_start(struct rte_eth_dev *dev) { uint16_t nb_queues, i; - struct virtnet_rx *rxvq; - struct virtnet_tx *txvq __rte_unused; + struct virtqueue *vq; struct virtio_hw *hw = dev->data->dev_private; int ret; @@ -2154,31 +2252,31 @@ virtio_dev_start(struct rte_eth_dev *dev) PMD_INIT_LOG(DEBUG, "nb_queues=%d", nb_queues); for (i = 0; i < dev->data->nb_rx_queues; i++) { - rxvq = dev->data->rx_queues[i]; + vq = virtnet_rxq_to_vq(dev->data->rx_queues[i]); /* Flush the old packets */ - virtqueue_rxvq_flush(rxvq->vq); - virtqueue_notify(rxvq->vq); + virtqueue_rxvq_flush(vq); + virtqueue_notify(vq); } for (i = 0; i < dev->data->nb_tx_queues; i++) { - txvq = dev->data->tx_queues[i]; - virtqueue_notify(txvq->vq); + vq = virtnet_txq_to_vq(dev->data->tx_queues[i]); + virtqueue_notify(vq); } PMD_INIT_LOG(DEBUG, "Notified backend at initialization"); for (i = 0; i < dev->data->nb_rx_queues; i++) { - rxvq = dev->data->rx_queues[i]; - VIRTQUEUE_DUMP(rxvq->vq); + vq = virtnet_rxq_to_vq(dev->data->rx_queues[i]); + VIRTQUEUE_DUMP(vq); } for (i = 0; i < dev->data->nb_tx_queues; i++) { - txvq = dev->data->tx_queues[i]; - VIRTQUEUE_DUMP(txvq->vq); + vq = virtnet_txq_to_vq(dev->data->tx_queues[i]); + VIRTQUEUE_DUMP(vq); } set_rxtx_funcs(dev); - hw->started = true; + hw->started = 1; /* Initialize Link state */ virtio_dev_link_update(dev, 0); @@ -2234,7 +2332,7 @@ static void virtio_dev_free_mbufs(struct rte_eth_dev *dev) /* * Stop device: disable interrupt and mark link down */ -static void +int virtio_dev_stop(struct rte_eth_dev *dev) { struct virtio_hw *hw = dev->data->dev_private; @@ -2242,11 +2340,12 @@ virtio_dev_stop(struct rte_eth_dev *dev) struct rte_intr_conf *intr_conf = &dev->data->dev_conf.intr_conf; PMD_INIT_LOG(DEBUG, "stop"); + dev->data->dev_started = 0; rte_spinlock_lock(&hw->state_lock); if (!hw->started) goto out_unlock; - hw->started = false; + hw->started = 0; if (intr_conf->lsc || intr_conf->rxq) { virtio_intr_disable(dev); @@ -2263,6 +2362,8 @@ virtio_dev_stop(struct rte_eth_dev *dev) rte_eth_linkstatus_set(dev, &link); out_unlock: rte_spinlock_unlock(&hw->state_lock); + + return 0; } static int @@ -2273,19 +2374,21 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet struct virtio_hw *hw = dev->data->dev_private; memset(&link, 0, sizeof(link)); - link.link_duplex = ETH_LINK_FULL_DUPLEX; - link.link_speed = ETH_SPEED_NUM_10G; - link.link_autoneg = ETH_LINK_FIXED; + link.link_duplex = hw->duplex; + link.link_speed = hw->speed; + link.link_autoneg = ETH_LINK_AUTONEG; if (!hw->started) { link.link_status = ETH_LINK_DOWN; - } else if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { + link.link_speed = ETH_SPEED_NUM_NONE; + } else if (virtio_with_feature(hw, VIRTIO_NET_F_STATUS)) { PMD_INIT_LOG(DEBUG, "Get link status from hw"); - vtpci_read_dev_config(hw, + virtio_read_dev_config(hw, offsetof(struct virtio_net_config, status), &status, sizeof(status)); if ((status & VIRTIO_NET_S_LINK_UP) == 0) { link.link_status = ETH_LINK_DOWN; + link.link_speed = ETH_SPEED_NUM_NONE; PMD_INIT_LOG(DEBUG, "Port %d is down", dev->data->port_id); } else { @@ -2309,7 +2412,7 @@ virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask) if (mask & ETH_VLAN_FILTER_MASK) { if ((offloads & DEV_RX_OFFLOAD_VLAN_FILTER) && - !vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { + !virtio_with_feature(hw, VIRTIO_NET_F_CTRL_VLAN)) { PMD_DRV_LOG(NOTICE, "vlan filtering not available on this host"); @@ -2324,13 +2427,12 @@ virtio_dev_vlan_offload_set(struct rte_eth_dev *dev, int mask) return 0; } -static void +static int virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) { uint64_t tso_mask, host_features; struct virtio_hw *hw = dev->data->dev_private; - - dev_info->speed_capa = ETH_LINK_SPEED_10G; /* fake value */ + dev_info->speed_capa = virtio_dev_speed_capa_get(hw->speed); dev_info->max_rx_queues = RTE_MIN(hw->max_queue_pairs, VIRTIO_MAX_RX_QUEUES); @@ -2340,7 +2442,7 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) dev_info->max_rx_pktlen = VIRTIO_MAX_RX_PKTLEN; dev_info->max_mac_addrs = VIRTIO_MAX_MAC_ADDRS; - host_features = VTPCI_OPS(hw)->get_features(hw); + host_features = VIRTIO_OPS(hw)->get_features(hw); 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)) { @@ -2366,6 +2468,8 @@ virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) (1ULL << VIRTIO_NET_F_HOST_TSO6); if ((host_features & tso_mask) == tso_mask) dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO; + + return 0; } /* @@ -2379,16 +2483,5 @@ __rte_unused uint8_t is_rx) return 0; } -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); -} +RTE_LOG_REGISTER(virtio_logtype_init, pmd.net.virtio.init, NOTICE); +RTE_LOG_REGISTER(virtio_logtype_driver, pmd.net.virtio.driver, NOTICE);