X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_pmd_virtio%2Fvirtio_ethdev.c;h=19930c06a594ac41495d7160354e44192bb0d57a;hb=565b85dcd9f48e47e7607086dddaa34f8b3c0b1c;hp=b5b9d01d8cdae408bfa011699b2d05b4b3c457c6;hpb=c1f86306a0261f50c503a73fea40293e2b2b724c;p=dpdk.git diff --git a/lib/librte_pmd_virtio/virtio_ethdev.c b/lib/librte_pmd_virtio/virtio_ethdev.c index b5b9d01d8c..19930c06a5 100644 --- a/lib/librte_pmd_virtio/virtio_ethdev.c +++ b/lib/librte_pmd_virtio/virtio_ethdev.c @@ -1,13 +1,13 @@ /*- * BSD LICENSE - * - * Copyright(c) 2010-2013 Intel Corporation. All rights reserved. + * + * Copyright(c) 2010-2014 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 @@ -17,7 +17,7 @@ * * 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 @@ -36,6 +36,9 @@ #include #include #include +#ifdef RTE_EXEC_ENV_LINUXAPP +#include +#endif #include #include @@ -50,6 +53,7 @@ #include #include +#include #include "virtio_ethdev.h" #include "virtio_pci.h" @@ -77,6 +81,12 @@ static void virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats * static void virtio_dev_stats_reset(struct rte_eth_dev *dev); static void virtio_dev_free_mbufs(struct rte_eth_dev *dev); +static int virtio_dev_queue_stats_mapping_set( + __rte_unused struct rte_eth_dev *eth_dev, + __rte_unused uint16_t queue_id, + __rte_unused uint8_t stat_idx, + __rte_unused uint8_t is_rx); + /* * The set of PCI devices this driver supports */ @@ -88,6 +98,134 @@ static struct rte_pci_id pci_id_virtio_map[] = { { .vendor_id = 0, /* sentinel */ }, }; +static int +virtio_send_command(struct virtqueue *vq, struct virtio_pmd_ctrl *ctrl, + int *dlen, int pkt_num) +{ + uint32_t head = vq->vq_desc_head_idx, i; + int k, sum = 0; + virtio_net_ctrl_ack status = ~0; + struct virtio_pmd_ctrl result; + + ctrl->status = status; + + if (!vq->hw->cvq) { + PMD_INIT_LOG(ERR, + "%s(): Control queue is not supported.", + __func__); + return -1; + } + + 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 < ((uint32_t)pkt_num + 2)) || (pkt_num < 1)) + return -1; + + memcpy(vq->virtio_net_hdr_mz->addr, ctrl, + sizeof(struct virtio_pmd_ctrl)); + + /* + * 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 = vq->virtio_net_hdr_mz->phys_addr; + vq->vq_ring.desc[head].len = sizeof(struct virtio_net_ctrl_hdr); + vq->vq_free_cnt--; + i = vq->vq_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 = vq->virtio_net_hdr_mz->phys_addr + + sizeof(struct virtio_net_ctrl_hdr) + + sizeof(ctrl->status) + sizeof(uint8_t)*sum; + vq->vq_ring.desc[i].len = dlen[k]; + sum += dlen[k]; + vq->vq_free_cnt--; + i = vq->vq_ring.desc[i].next; + } + + vq->vq_ring.desc[i].flags = VRING_DESC_F_WRITE; + vq->vq_ring.desc[i].addr = vq->virtio_net_hdr_mz->phys_addr + + sizeof(struct virtio_net_ctrl_hdr); + vq->vq_ring.desc[i].len = sizeof(ctrl->status); + vq->vq_free_cnt--; + + vq->vq_desc_head_idx = vq->vq_ring.desc[i].next; + + vq_update_avail_ring(vq, head); + vq_update_avail_idx(vq); + + PMD_INIT_LOG(DEBUG, "vq->vq_queue_index = %d", vq->vq_queue_index); + + virtqueue_notify(vq); + + while (vq->vq_used_cons_idx == vq->vq_ring.used->idx) + usleep(100); + + while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) { + uint32_t idx, desc_idx, used_idx; + struct vring_used_elem *uep; + + rmb(); + + used_idx = (uint32_t)(vq->vq_used_cons_idx + & (vq->vq_nentries - 1)); + uep = &vq->vq_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; + vq->vq_free_cnt++; + } + + vq->vq_ring.desc[desc_idx].next = vq->vq_desc_head_idx; + vq->vq_desc_head_idx = idx; + + vq->vq_used_cons_idx++; + vq->vq_free_cnt++; + } + + 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, vq->virtio_net_hdr_mz->addr, + sizeof(struct virtio_pmd_ctrl)); + + return result.status; +} + +static int +virtio_set_multiple_queues(struct rte_eth_dev *dev, uint16_t nb_queues) +{ + struct virtio_hw *hw + = VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); + struct virtio_pmd_ctrl ctrl; + int dlen[1]; + int ret; + + ctrl.hdr.class = VIRTIO_NET_CTRL_MQ; + ctrl.hdr.cmd = VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET; + memcpy(ctrl.data, &nb_queues, sizeof(uint16_t)); + + dlen[0] = sizeof(uint16_t); + + ret = virtio_send_command(hw->cvq, &ctrl, dlen, 1); + + if (ret) { + PMD_INIT_LOG(ERR, "Multiqueue configured but send command " + "failed, this is too late now..."); + return -EINVAL; + } + + return 0; +} + int virtio_dev_queue_setup(struct rte_eth_dev *dev, int queue_type, uint16_t queue_idx, @@ -100,57 +238,56 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev, const struct rte_memzone *mz; uint16_t vq_size; int size; - struct virtio_hw *hw = + struct virtio_hw *hw = VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); struct virtqueue *vq = NULL; /* Write the virtqueue index to the Queue Select Field */ VIRTIO_WRITE_REG_2(hw, VIRTIO_PCI_QUEUE_SEL, vtpci_queue_idx); - PMD_INIT_LOG(DEBUG, "selecting queue: %d\n", vtpci_queue_idx); + PMD_INIT_LOG(DEBUG, "selecting queue: %d", vtpci_queue_idx); /* * Read the virtqueue size from the Queue Size field * Always power of 2 and if 0 virtqueue does not exist */ vq_size = VIRTIO_READ_REG_2(hw, VIRTIO_PCI_QUEUE_NUM); - PMD_INIT_LOG(DEBUG, "vq_size: %d nb_desc:%d\n", vq_size, nb_desc); + PMD_INIT_LOG(DEBUG, "vq_size: %d nb_desc:%d", vq_size, nb_desc); if (nb_desc == 0) nb_desc = vq_size; if (vq_size == 0) { - PMD_INIT_LOG(ERR, "%s: virtqueue does not exist\n", __func__); - return (-EINVAL); + PMD_INIT_LOG(ERR, "%s: virtqueue does not exist", __func__); + return -EINVAL; } else if (!rte_is_power_of_2(vq_size)) { - PMD_INIT_LOG(ERR, "%s: virtqueue size is not powerof 2\n", __func__); - return (-EINVAL); + PMD_INIT_LOG(ERR, "%s: virtqueue size is not powerof 2", __func__); + return -EINVAL; } else if (nb_desc != vq_size) { - PMD_INIT_LOG(ERR, "Warning: nb_desc(%d) is not equal to vq size (%d), fall to vq size\n", + PMD_INIT_LOG(ERR, "Warning: nb_desc(%d) is not equal to vq size (%d), fall to vq size", nb_desc, vq_size); nb_desc = vq_size; } if (queue_type == VTNET_RQ) { - rte_snprintf(vq_name, sizeof(vq_name), "port%d_rvq%d", - dev->data->port_id, queue_idx); + snprintf(vq_name, sizeof(vq_name), "port%d_rvq%d", + dev->data->port_id, queue_idx); vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) + vq_size * sizeof(struct vq_desc_extra), CACHE_LINE_SIZE); - strncpy(vq->vq_name, vq_name, sizeof(vq->vq_name)); - } else if(queue_type == VTNET_TQ) { - rte_snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d", + } else if (queue_type == VTNET_TQ) { + snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d", dev->data->port_id, queue_idx); vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) + vq_size * sizeof(struct vq_desc_extra), CACHE_LINE_SIZE); - strncpy(vq->vq_name, vq_name, sizeof(vq->vq_name)); - } else if(queue_type == VTNET_CQ) { - rte_snprintf(vq_name, sizeof(vq_name), "port%d_cvq", - dev->data->port_id); - vq = rte_zmalloc(vq_name, sizeof(struct virtqueue), + } else if (queue_type == VTNET_CQ) { + snprintf(vq_name, sizeof(vq_name), "port%d_cvq", + dev->data->port_id); + vq = rte_zmalloc(vq_name, sizeof(struct virtqueue) + + vq_size * sizeof(struct vq_desc_extra), CACHE_LINE_SIZE); - strncpy(vq->vq_name, vq_name, sizeof(vq->vq_name)); } if (vq == NULL) { - PMD_INIT_LOG(ERR, "%s: Can not allocate virtqueue\n", __func__); - return (-ENOMEM); + PMD_INIT_LOG(ERR, "%s: Can not allocate virtqueue", __func__); + return (-ENOMEM); } + vq->hw = hw; vq->port_id = dev->data->port_id; vq->queue_id = queue_idx; @@ -164,59 +301,64 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev, */ size = vring_size(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\n", size, vq->vq_ring_size); + 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, 0, VIRTIO_PCI_VRING_ALIGN); + socket_id, 0, VIRTIO_PCI_VRING_ALIGN); if (mz == NULL) { rte_free(vq); - return (-ENOMEM); + return -ENOMEM; } + /* - * Virtio PCI device VIRTIO_PCI_QUEUE_PF register is 32bit, - * and only accepts 32 bit page frame number. - * Check if the allocated physical memory exceeds 16TB. - */ - if ( (mz->phys_addr + vq->vq_ring_size - 1) >> (VIRTIO_PCI_QUEUE_ADDR_SHIFT + 32) ) { - PMD_INIT_LOG(ERR, "vring address shouldn't be above 16TB!\n"); + * Virtio PCI device VIRTIO_PCI_QUEUE_PF register is 32bit, + * and only accepts 32 bit page frame number. + * Check if the allocated physical memory exceeds 16TB. + */ + if ((mz->phys_addr + vq->vq_ring_size - 1) >> (VIRTIO_PCI_QUEUE_ADDR_SHIFT + 32)) { + PMD_INIT_LOG(ERR, "vring address shouldn't be above 16TB!"); rte_free(vq); - return (-ENOMEM); + return -ENOMEM; } + memset(mz->addr, 0, sizeof(mz->len)); vq->mz = mz; vq->vq_ring_mem = mz->phys_addr; vq->vq_ring_virt_mem = mz->addr; - PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem: 0x%"PRIx64"\n", (uint64_t)mz->phys_addr); - PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%"PRIx64"\n", (uint64_t)mz->addr); + PMD_INIT_LOG(DEBUG, "vq->vq_ring_mem: 0x%"PRIx64, (uint64_t)mz->phys_addr); + PMD_INIT_LOG(DEBUG, "vq->vq_ring_virt_mem: 0x%"PRIx64, (uint64_t)mz->addr); vq->virtio_net_hdr_mz = NULL; - vq->virtio_net_hdr_mem = (void *)NULL; + vq->virtio_net_hdr_mem = 0; if (queue_type == VTNET_TQ) { - /* - * For each xmit packet, allocate a virtio_net_hdr - */ - rte_snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d_hdrzone", + /* + * For each xmit packet, allocate a virtio_net_hdr + */ + snprintf(vq_name, sizeof(vq_name), "port%d_tvq%d_hdrzone", dev->data->port_id, queue_idx); vq->virtio_net_hdr_mz = rte_memzone_reserve_aligned(vq_name, - vq_size * sizeof(struct virtio_net_hdr), + vq_size * hw->vtnet_hdr_size, socket_id, 0, CACHE_LINE_SIZE); if (vq->virtio_net_hdr_mz == NULL) { rte_free(vq); - return (-ENOMEM); + return -ENOMEM; } - vq->virtio_net_hdr_mem = (void *)(uintptr_t)vq->virtio_net_hdr_mz->phys_addr; - memset(vq->virtio_net_hdr_mz->addr, 0, vq_size * sizeof(struct virtio_net_hdr)); + vq->virtio_net_hdr_mem = + vq->virtio_net_hdr_mz->phys_addr; + memset(vq->virtio_net_hdr_mz->addr, 0, + vq_size * hw->vtnet_hdr_size); } else if (queue_type == VTNET_CQ) { /* Allocate a page for control vq command, data and status */ - rte_snprintf(vq_name, sizeof(vq_name), "port%d_cvq_hdrzone", + snprintf(vq_name, sizeof(vq_name), "port%d_cvq_hdrzone", dev->data->port_id); vq->virtio_net_hdr_mz = rte_memzone_reserve_aligned(vq_name, PAGE_SIZE, socket_id, 0, CACHE_LINE_SIZE); if (vq->virtio_net_hdr_mz == NULL) { rte_free(vq); - return (-ENOMEM); + return -ENOMEM; } - vq->virtio_net_hdr_mem = (void *)(uintptr_t)vq->virtio_net_hdr_mz->phys_addr; + vq->virtio_net_hdr_mem = + vq->virtio_net_hdr_mz->phys_addr; memset(vq->virtio_net_hdr_mz->addr, 0, PAGE_SIZE); } @@ -227,12 +369,12 @@ int virtio_dev_queue_setup(struct rte_eth_dev *dev, VIRTIO_WRITE_REG_4(hw, VIRTIO_PCI_QUEUE_PFN, mz->phys_addr >> VIRTIO_PCI_QUEUE_ADDR_SHIFT); *pvq = vq; - return (0); + return 0; } static int -virtio_dev_cq_queue_setup(struct rte_eth_dev *dev, - unsigned int socket_id) +virtio_dev_cq_queue_setup(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx, + uint32_t socket_id) { struct virtqueue *vq; uint16_t nb_desc = 0; @@ -241,35 +383,49 @@ virtio_dev_cq_queue_setup(struct rte_eth_dev *dev, VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); PMD_INIT_FUNC_TRACE(); - ret = virtio_dev_queue_setup(dev, VTNET_CQ, 0, VTNET_SQ_CQ_QUEUE_IDX, - nb_desc, socket_id, &vq); + ret = virtio_dev_queue_setup(dev, VTNET_CQ, VTNET_SQ_CQ_QUEUE_IDX, + vtpci_queue_idx, nb_desc, socket_id, &vq); + if (ret < 0) { - PMD_INIT_LOG(ERR, "control vq initialization failed\n"); + PMD_INIT_LOG(ERR, "control vq initialization failed"); return ret; } hw->cvq = vq; - return (0); + return 0; +} + +static void +virtio_dev_close(struct rte_eth_dev *dev) +{ + PMD_INIT_LOG(DEBUG, "virtio_dev_close"); + + virtio_dev_stop(dev); } /* * dev_ops for virtio, bare necessities for basic operation */ static struct eth_dev_ops virtio_eth_dev_ops = { - .dev_configure = virtio_dev_configure, - .dev_start = virtio_dev_start, - .dev_stop = virtio_dev_stop, - - .dev_infos_get = virtio_dev_info_get, - .stats_get = virtio_dev_stats_get, - .stats_reset = virtio_dev_stats_reset, - .link_update = virtio_dev_link_update, - .mac_addr_add = NULL, - .mac_addr_remove = NULL, - .rx_queue_setup = virtio_dev_rx_queue_setup, - .rx_queue_release = virtio_dev_rx_queue_release, /* meaningfull only to multiple queue */ - .tx_queue_setup = virtio_dev_tx_queue_setup, - .tx_queue_release = virtio_dev_tx_queue_release /* meaningfull only to multiple queue */ + .dev_configure = virtio_dev_configure, + .dev_start = virtio_dev_start, + .dev_stop = virtio_dev_stop, + .dev_close = virtio_dev_close, + + .dev_infos_get = virtio_dev_info_get, + .stats_get = virtio_dev_stats_get, + .stats_reset = virtio_dev_stats_reset, + .link_update = virtio_dev_link_update, + .mac_addr_add = NULL, + .mac_addr_remove = NULL, + .rx_queue_setup = virtio_dev_rx_queue_setup, + /* meaningfull only to multiple queue */ + .rx_queue_release = virtio_dev_rx_queue_release, + .tx_queue_setup = virtio_dev_tx_queue_setup, + /* meaningfull only to multiple queue */ + .tx_queue_release = virtio_dev_tx_queue_release, + /* collect stats per queue */ + .queue_stats_mapping_set = virtio_dev_queue_stats_mapping_set, }; static inline int @@ -281,9 +437,9 @@ virtio_dev_atomic_read_link_status(struct rte_eth_dev *dev, if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, *(uint64_t *)src) == 0) - return (-1); + return -1; - return (0); + return 0; } /** @@ -307,27 +463,75 @@ virtio_dev_atomic_write_link_status(struct rte_eth_dev *dev, if (rte_atomic64_cmpset((uint64_t *)dst, *(uint64_t *)dst, *(uint64_t *)src) == 0) - return (-1); + return -1; - return (0); + return 0; } static void virtio_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats) { - struct virtio_hw *hw = - VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); - if(stats) - memcpy(stats, &hw->eth_stats, sizeof(*stats)); + unsigned i; + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + const struct virtqueue *txvq = dev->data->tx_queues[i]; + if (txvq == NULL) + continue; + + stats->opackets += txvq->packets; + stats->obytes += txvq->bytes; + stats->oerrors += txvq->errors; + + if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) { + stats->q_opackets[i] = txvq->packets; + stats->q_obytes[i] = txvq->bytes; + } + } + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + const struct virtqueue *rxvq = dev->data->rx_queues[i]; + if (rxvq == NULL) + continue; + + stats->ipackets += rxvq->packets; + stats->ibytes += rxvq->bytes; + stats->ierrors += rxvq->errors; + + if (i < RTE_ETHDEV_QUEUE_STAT_CNTRS) { + stats->q_ipackets[i] = rxvq->packets; + stats->q_ibytes[i] = rxvq->bytes; + } + } + + stats->rx_nombuf = dev->data->rx_mbuf_alloc_failed; } static void virtio_dev_stats_reset(struct rte_eth_dev *dev) { - struct virtio_hw *hw = - VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); - /* Reset software totals */ - memset(&hw->eth_stats, 0, sizeof(hw->eth_stats)); + unsigned int i; + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + struct virtqueue *txvq = dev->data->tx_queues[i]; + if (txvq == NULL) + continue; + + txvq->packets = 0; + txvq->bytes = 0; + txvq->errors = 0; + } + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + struct virtqueue *rxvq = dev->data->rx_queues[i]; + if (rxvq == NULL) + continue; + + rxvq->packets = 0; + rxvq->bytes = 0; + rxvq->errors = 0; + } + + dev->data->rx_mbuf_alloc_failed = 0; } static void @@ -352,11 +556,13 @@ virtio_get_hwaddr(struct virtio_hw *hw) } -static void virtio_negotiate_features(struct virtio_hw *hw) +static void +virtio_negotiate_features(struct virtio_hw *hw) { - uint64_t guest_features, mask; - mask = VIRTIO_NET_F_CTRL_VQ | VIRTIO_NET_F_CTRL_RX | VIRTIO_NET_F_CTRL_VLAN; - mask |= VIRTIO_NET_F_CSUM | VIRTIO_NET_F_GUEST_CSUM ; + uint32_t host_features, mask; + + mask = VIRTIO_NET_F_CTRL_RX | VIRTIO_NET_F_CTRL_VLAN; + mask |= VIRTIO_NET_F_CSUM | VIRTIO_NET_F_GUEST_CSUM; /* TSO and LRO are only available when their corresponding * checksum offload feature is also negotiated. @@ -365,21 +571,149 @@ static void virtio_negotiate_features(struct virtio_hw *hw) mask |= VIRTIO_NET_F_GUEST_TSO4 | VIRTIO_NET_F_GUEST_TSO6 | VIRTIO_NET_F_GUEST_ECN; mask |= VTNET_LRO_FEATURES; - /* rx_mbuf should not be in multiple merged segments */ - mask |= VIRTIO_NET_F_MRG_RXBUF; - /* not negotiating INDIRECT descriptor table support */ mask |= VIRTIO_RING_F_INDIRECT_DESC; /* Prepare guest_features: feature that driver wants to support */ - guest_features = VTNET_FEATURES & ~mask; + hw->guest_features = VTNET_FEATURES & ~mask; + PMD_INIT_LOG(DEBUG, "guest_features before negotiate = %x", + hw->guest_features); /* Read device(host) feature bits */ - hw->host_features = VIRTIO_READ_REG_4(hw, VIRTIO_PCI_HOST_FEATURES); + host_features = VIRTIO_READ_REG_4(hw, VIRTIO_PCI_HOST_FEATURES); + PMD_INIT_LOG(DEBUG, "host_features before negotiate = %x", + host_features); + + /* + * Negotiate features: Subset of device feature bits are written back + * guest feature bits. + */ + hw->guest_features = vtpci_negotiate_features(hw, host_features); + PMD_INIT_LOG(DEBUG, "features after negotiate = %x", + hw->guest_features); +} + +#ifdef RTE_EXEC_ENV_LINUXAPP +static int +parse_sysfs_value(const char *filename, unsigned long *val) +{ + FILE *f; + char buf[BUFSIZ]; + char *end = NULL; + + f = fopen(filename, "r"); + if (f == NULL) { + PMD_INIT_LOG(ERR, "%s(): cannot open sysfs value %s", + __func__, filename); + return -1; + } + + if (fgets(buf, sizeof(buf), f) == NULL) { + PMD_INIT_LOG(ERR, "%s(): cannot read sysfs value %s", + __func__, filename); + fclose(f); + return -1; + } + *val = strtoul(buf, &end, 0); + if ((buf[0] == '\0') || (end == NULL) || (*end != '\n')) { + PMD_INIT_LOG(ERR, "%s(): cannot parse sysfs value %s", + __func__, filename); + fclose(f); + return -1; + } + fclose(f); + return 0; +} + +static int get_uio_dev(struct rte_pci_addr *loc, char *buf, unsigned int buflen) +{ + unsigned int uio_num; + struct dirent *e; + DIR *dir; + char dirname[PATH_MAX]; + + /* depending on kernel version, uio can be located in uio/uioX + * or uio:uioX */ + snprintf(dirname, sizeof(dirname), + SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/uio", + loc->domain, loc->bus, loc->devid, loc->function); + dir = opendir(dirname); + if (dir == NULL) { + /* retry with the parent directory */ + snprintf(dirname, sizeof(dirname), + SYSFS_PCI_DEVICES "/" PCI_PRI_FMT, + loc->domain, loc->bus, loc->devid, loc->function); + dir = opendir(dirname); + + if (dir == NULL) { + PMD_INIT_LOG(ERR, "Cannot opendir %s", dirname); + return -1; + } + } + + /* take the first file starting with "uio" */ + while ((e = readdir(dir)) != NULL) { + /* format could be uio%d ...*/ + int shortprefix_len = sizeof("uio") - 1; + /* ... or uio:uio%d */ + int longprefix_len = sizeof("uio:uio") - 1; + char *endptr; + + if (strncmp(e->d_name, "uio", 3) != 0) + continue; + + /* first try uio%d */ + errno = 0; + uio_num = strtoull(e->d_name + shortprefix_len, &endptr, 10); + if (errno == 0 && endptr != (e->d_name + shortprefix_len)) { + snprintf(buf, buflen, "%s/uio%u", dirname, uio_num); + break; + } + + /* then try uio:uio%d */ + errno = 0; + uio_num = strtoull(e->d_name + longprefix_len, &endptr, 10); + if (errno == 0 && endptr != (e->d_name + longprefix_len)) { + snprintf(buf, buflen, "%s/uio:uio%u", dirname, + uio_num); + break; + } + } + closedir(dir); + + /* No uio resource found */ + if (e == NULL) { + PMD_INIT_LOG(ERR, "Could not find uio resource"); + return -1; + } + + return 0; +} - /* Negotiate features: Subset of device feature bits are written back (guest feature bits) */ - hw->guest_features = vtpci_negotiate_features(hw, guest_features); +static int +virtio_has_msix(const struct rte_pci_addr *loc) +{ + DIR *d; + char dirname[PATH_MAX]; + + snprintf(dirname, sizeof(dirname), + SYSFS_PCI_DEVICES "/" PCI_PRI_FMT "/msi_irqs", + loc->domain, loc->bus, loc->devid, loc->function); + + d = opendir(dirname); + if (d) + closedir(d); + + return (d != NULL); +} +#else +static int +virtio_has_msix(const struct rte_pci_addr *loc __rte_unused) +{ + /* nic_uio does not enable interrupts, return 0 (false). */ + return 0; } +#endif /* * This function is based on probe() function in virtio_pci.c @@ -389,36 +723,62 @@ static int eth_virtio_dev_init(__rte_unused struct eth_driver *eth_drv, struct rte_eth_dev *eth_dev) { + struct virtio_net_config *config; + struct virtio_net_config local_config; + uint32_t offset_conf = sizeof(config->mac); struct rte_pci_device *pci_dev; struct virtio_hw *hw = VIRTIO_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private); - if (RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr) ) { - PMD_INIT_LOG(ERR, - "MBUF HEADROOM should be enough to hold virtio net hdr\n"); - return (-1); - } - if (! (rte_eal_get_configuration()->flags & EAL_FLG_HIGH_IOPL)) { + if (RTE_PKTMBUF_HEADROOM < sizeof(struct virtio_net_hdr)) { PMD_INIT_LOG(ERR, - "IOPL call failed in EAL init - cannot use virtio PMD driver\n"); - return (-1); + "MBUF HEADROOM should be enough to hold virtio net hdr\n"); + return -1; } eth_dev->dev_ops = &virtio_eth_dev_ops; - eth_dev->rx_pkt_burst = &virtio_recv_pkts; eth_dev->tx_pkt_burst = &virtio_xmit_pkts; - if(rte_eal_process_type() == RTE_PROC_SECONDARY) + if (rte_eal_process_type() == RTE_PROC_SECONDARY) return 0; pci_dev = eth_dev->pci_dev; - hw->device_id = pci_dev->id.device_id; - hw->vendor_id = pci_dev->id.vendor_id; - hw->io_base = (uint32_t)(uintptr_t)pci_dev->mem_resource[0].addr; +#ifdef RTE_EXEC_ENV_LINUXAPP + { + char dirname[PATH_MAX]; + char filename[PATH_MAX]; + unsigned long start, size; + + if (get_uio_dev(&pci_dev->addr, dirname, sizeof(dirname)) < 0) + return -1; + + /* get portio size */ + snprintf(filename, sizeof(filename), + "%s/portio/port0/size", dirname); + if (parse_sysfs_value(filename, &size) < 0) { + PMD_INIT_LOG(ERR, "%s(): cannot parse size", + __func__); + return -1; + } - hw->max_rx_queues = VIRTIO_MAX_RX_QUEUES; - hw->max_tx_queues = VIRTIO_MAX_TX_QUEUES; + /* get portio start */ + snprintf(filename, sizeof(filename), + "%s/portio/port0/start", dirname); + if (parse_sysfs_value(filename, &start) < 0) { + PMD_INIT_LOG(ERR, "%s(): cannot parse portio start", + __func__); + return -1; + } + pci_dev->mem_resource[0].addr = (void *)(uintptr_t)start; + pci_dev->mem_resource[0].len = (uint64_t)size; + PMD_INIT_LOG(DEBUG, + "PCI Port IO found start=0x%lx with size=0x%lx", + start, size); + } +#endif + hw->use_msix = virtio_has_msix(&pci_dev->addr); + hw->io_base = (uint32_t)(uintptr_t)pci_dev->mem_resource[0].addr; /* Reset the device although not necessary at startup */ vtpci_reset(hw); @@ -429,11 +789,15 @@ eth_virtio_dev_init(__rte_unused struct eth_driver *eth_drv, /* Tell the host we've known how to drive the device. */ vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER); virtio_negotiate_features(hw); + /* Setting up rx_header size for the device */ - if(vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) { + eth_dev->rx_pkt_burst = &virtio_recv_mergeable_pkts; hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf); - else + } else { + eth_dev->rx_pkt_burst = &virtio_recv_pkts; hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr); + } /* Allocate memory for storing MAC addresses */ eth_dev->data->mac_addrs = rte_zmalloc("virtio", ETHER_ADDR_LEN, 0); @@ -441,31 +805,79 @@ eth_virtio_dev_init(__rte_unused struct eth_driver *eth_drv, PMD_INIT_LOG(ERR, "Failed to allocate %d bytes needed to store MAC addresses", ETHER_ADDR_LEN); - return (-ENOMEM); + return -ENOMEM; } + /* Copy the permanent MAC address to: virtio_hw */ virtio_get_hwaddr(hw); ether_addr_copy((struct ether_addr *) hw->mac_addr, ð_dev->data->mac_addrs[0]); - PMD_INIT_LOG(DEBUG, "PORT MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", hw->mac_addr[0], - hw->mac_addr[1],hw->mac_addr[2], hw->mac_addr[3], hw->mac_addr[4], hw->mac_addr[5]); + 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)) - virtio_dev_cq_queue_setup(eth_dev, SOCKET_ID_ANY); + if (vtpci_with_feature(hw, VIRTIO_NET_F_CTRL_VQ)) { + config = &local_config; + if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { + offset_conf += sizeof(config->status); + } else { + PMD_INIT_LOG(DEBUG, + "VIRTIO_NET_F_STATUS is not supported"); + config->status = 0; + } + + if (vtpci_with_feature(hw, VIRTIO_NET_F_MQ)) { + offset_conf += sizeof(config->max_virtqueue_pairs); + } else { + PMD_INIT_LOG(DEBUG, + "VIRTIO_NET_F_MQ is not supported"); + config->max_virtqueue_pairs = 1; + } + + vtpci_read_dev_config(hw, 0, (uint8_t *)config, offset_conf); + + hw->max_rx_queues = + (VIRTIO_MAX_RX_QUEUES < config->max_virtqueue_pairs) ? + VIRTIO_MAX_RX_QUEUES : config->max_virtqueue_pairs; + hw->max_tx_queues = + (VIRTIO_MAX_TX_QUEUES < config->max_virtqueue_pairs) ? + VIRTIO_MAX_TX_QUEUES : config->max_virtqueue_pairs; + + virtio_dev_cq_queue_setup(eth_dev, + config->max_virtqueue_pairs * 2, + SOCKET_ID_ANY); + + PMD_INIT_LOG(DEBUG, "config->max_virtqueue_pairs=%d", + config->max_virtqueue_pairs); + PMD_INIT_LOG(DEBUG, "config->status=%d", config->status); + PMD_INIT_LOG(DEBUG, + "PORT MAC: %02X:%02X:%02X:%02X:%02X:%02X", + config->mac[0], config->mac[1], + config->mac[2], config->mac[3], + config->mac[4], config->mac[5]); + } else { + hw->max_rx_queues = 1; + hw->max_tx_queues = 1; + } + + eth_dev->data->nb_rx_queues = hw->max_rx_queues; + eth_dev->data->nb_tx_queues = hw->max_tx_queues; + + PMD_INIT_LOG(DEBUG, "hw->max_rx_queues=%d hw->max_tx_queues=%d", + hw->max_rx_queues, hw->max_tx_queues); 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); + return 0; } static struct eth_driver rte_virtio_pmd = { { .name = "rte_virtio_pmd", .id_table = pci_id_virtio_map, -#ifdef RTE_EAL_UNBIND_PORTS - .drv_flags = RTE_PCI_DRV_NEED_IGB_UIO, -#endif + .drv_flags = RTE_PCI_DRV_NEED_MAPPING, }, .eth_dev_init = eth_virtio_dev_init, .dev_private_size = sizeof(struct virtio_adapter), @@ -477,11 +889,17 @@ static struct eth_driver rte_virtio_pmd = { * Register itself as the [Poll Mode] Driver of PCI virtio devices. * Returns 0 on success. */ -int -rte_virtio_pmd_init(void) +static int +rte_virtio_pmd_init(const char *name __rte_unused, + const char *param __rte_unused) { + if (rte_eal_iopl_init() != 0) { + PMD_INIT_LOG(ERR, "IOPL call failed - cannot use virtio PMD"); + return -1; + } + rte_eth_driver_register(&rte_virtio_pmd); - return (0); + return 0; } /* @@ -502,15 +920,25 @@ virtio_dev_tx_queue_release(__rte_unused void *txq) * It returns 0 on success. */ static int -virtio_dev_configure(__rte_unused struct rte_eth_dev *dev) +virtio_dev_configure(struct rte_eth_dev *dev) { - return (0); + const struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode; + + PMD_INIT_LOG(DEBUG, "configure"); + + if (rxmode->hw_ip_checksum) { + PMD_DRV_LOG(ERR, "HW IP checksum not supported"); + return (-EINVAL); + } + + return 0; } static int virtio_dev_start(struct rte_eth_dev *dev) { + uint16_t nb_queues, i; uint16_t status; struct virtio_hw *hw = VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); @@ -521,22 +949,23 @@ virtio_dev_start(struct rte_eth_dev *dev) /* Tell the host we've known how to drive the device. */ vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER); - hw->adapter_stopped = 0; + virtio_dev_cq_start(dev); /* Do final configuration before rx/tx engine starts */ virtio_dev_rxtx_start(dev); /* Check VIRTIO_NET_F_STATUS for link status*/ - if(vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { - + 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_LINK_UP) == 0) { - PMD_INIT_LOG(ERR, "Port: %d Link is DOWN\n", dev->data->port_id); - return (-EIO); + if ((status & VIRTIO_NET_S_LINK_UP) == 0) { + PMD_INIT_LOG(ERR, "Port: %d Link is DOWN", + dev->data->port_id); + return -EIO; } else { - PMD_INIT_LOG(DEBUG, "Port: %d Link is UP\n", dev->data->port_id); + PMD_INIT_LOG(DEBUG, "Port: %d Link is UP", + dev->data->port_id); } } vtpci_reinit_complete(hw); @@ -545,34 +974,69 @@ virtio_dev_start(struct rte_eth_dev *dev) *Otherwise the tap backend might already stop its queue due to fullness. *vhost backend will have no chance to be waked up */ - virtqueue_notify(dev->data->rx_queues[0]); - PMD_INIT_LOG(DEBUG, "Notified backend at initialization\n"); - return (0); + nb_queues = dev->data->nb_rx_queues; + if (nb_queues > 1) { + if (virtio_set_multiple_queues(dev, nb_queues) != 0) + return -EINVAL; + } + + PMD_INIT_LOG(DEBUG, "nb_queues=%d", nb_queues); + + for (i = 0; i < nb_queues; i++) + virtqueue_notify(dev->data->rx_queues[i]); + + PMD_INIT_LOG(DEBUG, "Notified backend at initialization"); + + for (i = 0; i < dev->data->nb_rx_queues; i++) + VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]); + + for (i = 0; i < dev->data->nb_tx_queues; i++) + VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[i]); + + return 0; } static void virtio_dev_free_mbufs(struct rte_eth_dev *dev) { - struct rte_mbuf * buf; - int i = 0; - PMD_INIT_LOG(DEBUG, "Before freeing rxq used and unused buf \n"); - VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[0]); - while( (buf =(struct rte_mbuf *)virtqueue_detatch_unused(dev->data->rx_queues[0])) != NULL) { - rte_pktmbuf_free_seg(buf); - i++; - } - PMD_INIT_LOG(DEBUG, "free %d mbufs\n", i); - PMD_INIT_LOG(DEBUG, "After freeing rxq used and unused buf\n"); - VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[0]); - PMD_INIT_LOG(DEBUG, "Before freeing txq used and unused bufs\n"); - VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[0]); - i = 0; - while( (buf = (struct rte_mbuf *)virtqueue_detatch_unused(dev->data->tx_queues[0])) != NULL) { - rte_pktmbuf_free_seg(buf); - i++; - } - PMD_INIT_LOG(DEBUG, "free %d mbufs\n", i); - PMD_INIT_LOG(DEBUG, "After freeing txq used and unused buf\n"); - VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[0]); + struct rte_mbuf *buf; + int i, mbuf_num = 0; + + for (i = 0; i < dev->data->nb_rx_queues; i++) { + PMD_INIT_LOG(DEBUG, + "Before freeing rxq[%d] used and unused buf", i); + VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]); + + while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused( + dev->data->rx_queues[i])) != NULL) { + rte_pktmbuf_free(buf); + mbuf_num++; + } + + PMD_INIT_LOG(DEBUG, "free %d mbufs", mbuf_num); + PMD_INIT_LOG(DEBUG, + "After freeing rxq[%d] used and unused buf", i); + VIRTQUEUE_DUMP((struct virtqueue *)dev->data->rx_queues[i]); + } + + for (i = 0; i < dev->data->nb_tx_queues; i++) { + PMD_INIT_LOG(DEBUG, + "Before freeing txq[%d] used and unused bufs", + i); + VIRTQUEUE_DUMP((struct virtqueue *)dev->data->tx_queues[i]); + + mbuf_num = 0; + while ((buf = (struct rte_mbuf *)virtqueue_detatch_unused( + dev->data->tx_queues[i])) != 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((struct virtqueue *)dev->data->tx_queues[i]); + } } /* @@ -595,38 +1059,41 @@ virtio_dev_link_update(struct rte_eth_dev *dev, __rte_unused int wait_to_complet struct rte_eth_link link, old; uint16_t status; struct virtio_hw *hw = - VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); + VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); memset(&link, 0, sizeof(link)); virtio_dev_atomic_read_link_status(dev, &link); old = link; - link.link_duplex = FULL_DUPLEX ; - link.link_speed = SPEED_10G ; - if(vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { - PMD_INIT_LOG(DEBUG, "Get link status from hw\n"); + link.link_duplex = FULL_DUPLEX; + link.link_speed = SPEED_10G; + if (vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) { + PMD_INIT_LOG(DEBUG, "Get link status from hw"); vtpci_read_dev_config(hw, offsetof(struct virtio_net_config, status), &status, sizeof(status)); - if((status & VIRTIO_NET_S_LINK_UP) == 0) { + if ((status & VIRTIO_NET_S_LINK_UP) == 0) { link.link_status = 0; - PMD_INIT_LOG(DEBUG, "Port %d is down\n",dev->data->port_id); + PMD_INIT_LOG(DEBUG, "Port %d is down", + dev->data->port_id); } else { link.link_status = 1; - PMD_INIT_LOG(DEBUG, "Port %d is up\n",dev->data->port_id); + PMD_INIT_LOG(DEBUG, "Port %d is up", + dev->data->port_id); } } else { - link.link_status = 1; //Link up + link.link_status = 1; /* Link up */ } virtio_dev_atomic_write_link_status(dev, &link); - if(old.link_status == link.link_status) - return (-1); + if (old.link_status == link.link_status) + return -1; /*changed*/ - return (0); + return 0; } static void virtio_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info) { struct virtio_hw *hw = VIRTIO_DEV_PRIVATE_TO_HW(dev->data->dev_private); + dev_info->driver_name = dev->driver->pci_drv.name; dev_info->max_rx_queues = (uint16_t)hw->max_rx_queues; dev_info->max_tx_queues = (uint16_t)hw->max_tx_queues; @@ -634,3 +1101,21 @@ 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; } + +/* + * It enables testpmd to collect per queue stats. + */ +static int +virtio_dev_queue_stats_mapping_set(__rte_unused struct rte_eth_dev *eth_dev, +__rte_unused uint16_t queue_id, __rte_unused uint8_t stat_idx, +__rte_unused uint8_t is_rx) +{ + return 0; +} + +static struct rte_driver rte_virtio_driver = { + .type = PMD_PDEV, + .init = rte_virtio_pmd_init, +}; + +PMD_REGISTER_DRIVER(rte_virtio_driver);