Sorry, CC mail-list
On 20.10.2016 17:20, Ilya Maximets wrote: > Not a complete review. > Few comments inline. > > Best regards, Ilya Maximets. > > On 14.10.2016 17:08, Ciara Loftus wrote: >> The vHost PMD allows vHost User ports to be controlled by the >> librte_ether API, like physical 'dpdk' ports and IVSHM 'dpdkr' ports. >> This commit integrates this PMD into OVS and removes direct calls to the >> librte_vhost DPDK library. >> >> This commit requires DPDK v16.11 functionality that isn't available in >> previous releases, and thus breaks compatibility with such releases. >> >> Signed-off-by: Ciara Loftus <ciara.lof...@intel.com> >> --- >> INSTALL.DPDK.md | 10 + >> NEWS | 2 + >> lib/netdev-dpdk.c | 1101 >> +++++++++++++++++++++-------------------------------- >> 3 files changed, 447 insertions(+), 666 deletions(-) >> >> diff --git a/INSTALL.DPDK.md b/INSTALL.DPDK.md >> index 2f0ae9a..5678e41 100644 >> --- a/INSTALL.DPDK.md >> +++ b/INSTALL.DPDK.md >> @@ -603,6 +603,16 @@ can be found in [Vhost Walkthrough]. >> >> http://dpdk.org/doc/guides/rel_notes/release_16.11.html >> >> + - dpdk, dpdkr and dpdkvhostuser ports are 'eth' type ports in the context >> of >> + DPDK as they are all managed by the rte_ether API. This means that they >> + adhere to the DPDK configuration option CONFIG_RTE_MAX_ETHPORTS which by >> + default is set to 32. This means by default the combined total number of >> + dpdk, dpdkr and dpdkvhostuser ports allowable in OVS with DPDK is 32. >> This >> + value can be changed if desired by modifying the configuration file in >> + DPDK, or by overriding the default value on the command line when >> building >> + DPDK. eg. >> + >> + `make install CONFIG_RTE_MAX_ETHPORTS=64` >> >> Bug Reporting: >> -------------- >> diff --git a/NEWS b/NEWS >> index ab74fcd..6e47683 100644 >> --- a/NEWS >> +++ b/NEWS >> @@ -135,6 +135,8 @@ v2.6.0 - 27 Sep 2016 >> * Remove dpdkvhostcuse port type. >> * OVS client mode for vHost and vHost reconnect (Requires QEMU 2.7) >> * 'dpdkvhostuserclient' port type. >> + * vHost PMD integration brings vhost-user ports under control of the >> + rte_ether DPDK API. >> - Increase number of registers to 16. >> - ovs-benchmark: This utility has been removed due to lack of use and >> bitrot. >> diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c >> index 7c1523e..d0b80a7 100644 >> --- a/lib/netdev-dpdk.c >> +++ b/lib/netdev-dpdk.c >> @@ -27,6 +27,7 @@ >> #include <rte_cycles.h> >> #include <rte_errno.h> >> #include <rte_eth_ring.h> >> +#include <rte_eth_vhost.h> >> #include <rte_ethdev.h> >> #include <rte_malloc.h> >> #include <rte_mbuf.h> >> @@ -122,6 +123,7 @@ BUILD_ASSERT_DECL((MAX_NB_MBUF / >> ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF)) >> #define XSTAT_RX_BROADCAST_PACKETS "rx_broadcast_packets" >> #define XSTAT_TX_BROADCAST_PACKETS "tx_broadcast_packets" >> #define XSTAT_RX_UNDERSIZED_ERRORS "rx_undersized_errors" >> +#define XSTAT_RX_UNDERSIZE_PACKETS "rx_undersize_packets" >> #define XSTAT_RX_OVERSIZE_ERRORS "rx_oversize_errors" >> #define XSTAT_RX_FRAGMENTED_ERRORS "rx_fragmented_errors" >> #define XSTAT_RX_JABBER_ERRORS "rx_jabber_errors" >> @@ -143,6 +145,9 @@ BUILD_ASSERT_DECL((MAX_NB_MBUF / >> ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF)) >> #define VHOST_ENQ_RETRY_NUM 8 >> #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ) >> >> +/* Array that tracks the used & unused vHost user driver IDs */ >> +static unsigned int vhost_drv_ids[RTE_MAX_ETHPORTS]; >> + >> static const struct rte_eth_conf port_conf = { >> .rxmode = { >> .mq_mode = ETH_MQ_RX_RSS, >> @@ -343,15 +348,12 @@ struct netdev_dpdk { >> struct rte_eth_link link; >> int link_reset_cnt; >> >> - /* virtio identifier for vhost devices */ >> - ovsrcu_index vid; >> - >> - /* True if vHost device is 'up' and has been reconfigured at least once >> */ >> - bool vhost_reconfigured; >> - >> /* Identifier used to distinguish vhost devices from each other. */ >> char vhost_id[PATH_MAX]; >> >> + /* ID of vhost user port given to the PMD driver */ >> + unsigned int vhost_pmd_id; >> + >> /* In dpdk_list. */ >> struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex); >> >> @@ -392,16 +394,25 @@ struct netdev_rxq_dpdk { >> }; >> >> static int netdev_dpdk_construct(struct netdev *); >> - >> -int netdev_dpdk_get_vid(const struct netdev_dpdk *dev); >> +static int netdev_dpdk_vhost_construct(struct netdev *); >> +static int netdev_dpdk_vhost_client_construct(struct netdev *); >> >> struct ingress_policer * >> netdev_dpdk_get_ingress_policer(const struct netdev_dpdk *dev); >> >> +static void link_status_changed_callback(uint8_t port_id, >> + enum rte_eth_event_type type, void *param); >> +static void vring_state_changed_callback(uint8_t port_id, >> + enum rte_eth_event_type type, void *param); >> +static void netdev_dpdk_remap_txqs(struct netdev_dpdk *dev); >> +static void netdev_dpdk_txq_map_clear(struct netdev_dpdk *dev); >> + >> static bool >> -is_dpdk_class(const struct netdev_class *class) >> +is_dpdk_eth_class(const struct netdev_class *class) >> { >> - return class->construct == netdev_dpdk_construct; >> + return ((class->construct == netdev_dpdk_construct) || >> + (class->construct == netdev_dpdk_vhost_construct) || >> + (class->construct == netdev_dpdk_vhost_client_construct)); >> } >> >> /* DPDK NIC drivers allocate RX buffers at a particular granularity, >> typically >> @@ -681,8 +692,13 @@ dpdk_eth_dev_queue_setup(struct netdev_dpdk *dev, int >> n_rxq, int n_txq) >> continue; >> } >> >> - dev->up.n_rxq = n_rxq; >> - dev->up.n_txq = n_txq; >> + /* Only set n_*xq for physical devices. vHost User devices will set >> + * this value correctly using info from the virtio backend. >> + */ >> + if (dev->type == DPDK_DEV_ETH) { >> + dev->up.n_rxq = n_rxq; >> + dev->up.n_txq = n_txq; >> + } >> >> return 0; >> } >> @@ -714,8 +730,16 @@ dpdk_eth_dev_init(struct netdev_dpdk *dev) >> >> rte_eth_dev_info_get(dev->port_id, &info); >> >> - n_rxq = MIN(info.max_rx_queues, dev->up.n_rxq); >> - n_txq = MIN(info.max_tx_queues, dev->up.n_txq); >> + if (dev->type == DPDK_DEV_VHOST) { >> + /* We don't know how many queues QEMU will use so we need to set up >> + * the max. If we configure less than what QEMU configures, those >> + * additional queues will not be available to us. */ >> + n_rxq = MIN(OVS_VHOST_MAX_QUEUE_NUM, RTE_MAX_QUEUES_PER_PORT); >> + n_txq = MIN(OVS_VHOST_MAX_QUEUE_NUM, RTE_MAX_QUEUES_PER_PORT); >> + } else { >> + n_rxq = MIN(info.max_rx_queues, dev->up.n_rxq); >> + n_txq = MIN(info.max_tx_queues, dev->up.n_txq); >> + } >> >> diag = dpdk_eth_dev_queue_setup(dev, n_rxq, n_txq); >> if (diag) { >> @@ -794,6 +818,93 @@ netdev_dpdk_alloc_txq(unsigned int n_txqs) >> return txqs; >> } >> >> +void >> +link_status_changed_callback(uint8_t port_id, >> + enum rte_eth_event_type type OVS_UNUSED, >> + void *param OVS_UNUSED) >> +{ >> + struct netdev_dpdk *dev; >> + int newnode = -1; >> + >> + ovs_mutex_lock(&dpdk_mutex); >> + LIST_FOR_EACH (dev, list_node, &dpdk_list) { >> + if (port_id == dev->port_id) { >> + ovs_mutex_lock(&dev->mutex); >> + check_link_status(dev); >> + if (dev->link.link_status == ETH_LINK_UP) { >> + /* Device brought up */ >> + /* Get queue information */ >> + int vid = rte_eth_vhost_get_vid_from_port_id(dev->port_id); >> + uint32_t qp_num = rte_vhost_get_queue_num(vid); >> + if (qp_num <= 0) { >> + qp_num = dev->requested_n_rxq; >> + } >> + /* Get NUMA information */ >> + newnode = rte_eth_dev_socket_id(dev->port_id); >> + if (newnode == -1) { >> + newnode = dev->socket_id; >> + } >> + if (dev->requested_n_txq != qp_num >> + || dev->requested_n_rxq != qp_num >> + || dev->requested_socket_id != newnode) { >> + dev->requested_socket_id = newnode; >> + dev->requested_n_rxq = qp_num; >> + dev->requested_n_txq = qp_num; >> + netdev_request_reconfigure(&dev->up); >> + } >> + netdev_change_seq_changed(&dev->up); >> + VLOG_INFO("vHost Device '%s' has been added on numa node >> %i", >> + dev->vhost_id, newnode); >> + } else { >> + /* Device brought down */ >> + /* Clear tx/rx queue settings. */ >> + netdev_dpdk_txq_map_clear(dev); >> + netdev_change_seq_changed(&dev->up); >> + VLOG_INFO("vHost Device '%s' has been removed", >> dev->vhost_id); >> + } >> + ovs_mutex_unlock(&dev->mutex); >> + break; >> + } >> + } >> + >> + ovs_mutex_unlock(&dpdk_mutex); >> + >> + return; >> +} >> + >> +void >> +vring_state_changed_callback(uint8_t port_id, >> + enum rte_eth_event_type type OVS_UNUSED, >> + void *param OVS_UNUSED) >> +{ >> + struct netdev_dpdk *dev; >> + struct rte_eth_vhost_queue_event event; >> + int err = 0; >> + >> + err = rte_eth_vhost_get_queue_event(port_id, &event); >> + if (err || event.rx) { >> + return; >> + } >> + >> + ovs_mutex_lock(&dpdk_mutex); >> + LIST_FOR_EACH (dev, list_node, &dpdk_list) { >> + if (port_id == dev->port_id) { >> + ovs_mutex_lock(&dev->mutex); >> + if (event.enable) { >> + dev->tx_q[event.queue_id].map = event.queue_id; >> + } else { >> + dev->tx_q[event.queue_id].map = OVS_VHOST_QUEUE_DISABLED; >> + } >> + netdev_dpdk_remap_txqs(dev); >> + ovs_mutex_unlock(&dev->mutex); >> + break; >> + } >> + } >> + ovs_mutex_unlock(&dpdk_mutex); >> + >> + return; >> +} >> + >> static int >> netdev_dpdk_init(struct netdev *netdev, unsigned int port_no, >> enum dpdk_dev_type type) >> @@ -802,6 +913,7 @@ netdev_dpdk_init(struct netdev *netdev, unsigned int >> port_no, >> struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> int sid; >> int err = 0; >> + unsigned int nr_q = 0; >> >> ovs_mutex_init(&dev->mutex); >> ovs_mutex_lock(&dev->mutex); >> @@ -811,11 +923,7 @@ netdev_dpdk_init(struct netdev *netdev, unsigned int >> port_no, >> /* If the 'sid' is negative, it means that the kernel fails >> * to obtain the pci numa info. In that situation, always >> * use 'SOCKET0'. */ >> - if (type == DPDK_DEV_ETH) { >> - sid = rte_eth_dev_socket_id(port_no); >> - } else { >> - sid = rte_lcore_to_socket_id(rte_get_master_lcore()); > > Why this branch was deleted? Without this vhostuserclient ports always will > use SOCKET0 in VHOST_NUMA disabled even if whole app works on SOCKET1. > >> - } >> + sid = rte_eth_dev_socket_id(port_no); >> >> dev->socket_id = sid < 0 ? SOCKET0 : sid; >> dev->requested_socket_id = dev->socket_id; >> @@ -824,8 +932,7 @@ netdev_dpdk_init(struct netdev *netdev, unsigned int >> port_no, >> dev->flags = 0; >> dev->requested_mtu = dev->mtu = ETHER_MTU; >> dev->max_packet_len = MTU_TO_FRAME_LEN(dev->mtu); >> - ovsrcu_index_init(&dev->vid, -1); >> - dev->vhost_reconfigured = false; >> + dev->vhost_driver_flags &= ~RTE_VHOST_USER_CLIENT; >> >> err = netdev_dpdk_mempool_configure(dev); >> if (err) { >> @@ -849,16 +956,21 @@ netdev_dpdk_init(struct netdev *netdev, unsigned int >> port_no, >> >> /* Initialize the flow control to NULL */ >> memset(&dev->fc_conf, 0, sizeof dev->fc_conf); >> - if (type == DPDK_DEV_ETH) { >> + if (port_no != -1) { > > How about new type DPDK_DEV_VHOST_CLIENT ? > All this stuff with 'port_no == -1' looks very confusing and hides > real meaning of 'if's. And without comments here it's pretty hard > to understand what's going on. > > >> err = dpdk_eth_dev_init(dev); >> if (err) { >> goto unlock; >> } >> - dev->tx_q = netdev_dpdk_alloc_txq(netdev->n_txq); >> - } else { >> - dev->tx_q = netdev_dpdk_alloc_txq(OVS_VHOST_MAX_QUEUE_NUM); >> - /* Enable DPDK_DEV_VHOST device and set promiscuous mode flag. */ >> - dev->flags = NETDEV_UP | NETDEV_PROMISC; >> + } >> + nr_q = (type == DPDK_DEV_ETH ? >> + 1 : MIN(OVS_VHOST_MAX_QUEUE_NUM, RTE_MAX_QUEUES_PER_PORT)); > > Why 1? It was 'netdev->n_txq'. > >> + dev->tx_q = netdev_dpdk_alloc_txq(nr_q); >> + >> + if (type == DPDK_DEV_VHOST && port_no != -1) { >> + rte_eth_dev_callback_register(port_no, RTE_ETH_EVENT_QUEUE_STATE, >> + vring_state_changed_callback, NULL); >> + rte_eth_dev_callback_register(port_no, RTE_ETH_EVENT_INTR_LSC, >> + link_status_changed_callback, NULL); >> } >> >> if (!dev->tx_q) { > > There is a race condition here. Checking for 'dev->tx_q' must be before > callback registering. Otherwise there will be some time between unlock > and return, where 'tx_q' can be used inside the callback. > >> @@ -894,6 +1006,66 @@ dpdk_dev_parse_name(const char dev_name[], const char >> prefix[], >> } >> } >> >> +/* When attaching a vhost device to DPDK, a unique name of the format >> + * 'net_vhostX' is expected, where X is a unique identifier. >> + * get_vhost_drv_id returns a valid X value to provide to DPDK. >> + */ >> +static int >> +get_vhost_drv_id(void) >> +{ >> + int i = 0; >> + >> + for (i = 0; i < RTE_MAX_ETHPORTS; i++) { >> + if (vhost_drv_ids[i] == 0) { >> + return i; >> + } >> + } >> + >> + return -1; >> +} >> + >> +static void >> +set_vhost_drv_id(int id, int val) >> +{ >> + vhost_drv_ids[id] = val; >> +} > > I think we can just increment global atomic counter instead of above solution. > Numbers just need to be uniqe. Driver never use them for anything. > >> + >> +static int >> +dpdk_attach_vhost_pmd(struct netdev_dpdk *dev, int mode) >> +{ >> + char *devargs; >> + int err = 0; >> + uint8_t port_no = 0; >> + int driver_id = 0; >> + >> + driver_id = get_vhost_drv_id(); >> + if (driver_id == -1) { >> + VLOG_ERR("Unable to create vhost-user device %s - too many >> vhost-user" >> + "devices registered with PMD", dev->vhost_id); >> + err = ENODEV; >> + } else { >> + devargs = xasprintf("net_vhost%u,iface=%s,queues=%i,client=%i", >> + driver_id, dev->vhost_id, >> + MIN(OVS_VHOST_MAX_QUEUE_NUM, RTE_MAX_QUEUES_PER_PORT), >> + mode); >> + err = rte_eth_dev_attach(devargs, &port_no); >> + if (!err) { >> + dev->port_id = port_no; >> + } >> + } >> + >> + if (err) { >> + VLOG_ERR("Failed to attach vhost-user device %s to DPDK", >> + dev->vhost_id); >> + } else { >> + /* Configuration successful */ >> + dev->vhost_pmd_id = driver_id; >> + set_vhost_drv_id(driver_id, 1); >> + } >> + >> + return err; >> +} >> + >> static int >> netdev_dpdk_vhost_construct(struct netdev *netdev) >> { >> @@ -904,7 +1076,7 @@ netdev_dpdk_vhost_construct(struct netdev *netdev) >> /* 'name' is appended to 'vhost_sock_dir' and used to create a socket in >> * the file system. '/' or '\' would traverse directories, so they're >> not >> * acceptable in 'name'. */ >> - if (strchr(name, '/') || strchr(name, '\\')) { >> + if (strchr(name, '/') || strchr(name, '\\') || strchr(name, ',')) { >> VLOG_ERR("\"%s\" is not a valid name for a vhost-user port. " >> "A valid name must not include '/' or '\\'", >> name); >> @@ -917,18 +1089,16 @@ netdev_dpdk_vhost_construct(struct netdev *netdev) >> */ >> snprintf(dev->vhost_id, sizeof dev->vhost_id, "%s/%s", >> dpdk_get_vhost_sock_dir(), name); >> + dev->port_id = -1; >> >> - dev->vhost_driver_flags &= ~RTE_VHOST_USER_CLIENT; >> - err = rte_vhost_driver_register(dev->vhost_id, dev->vhost_driver_flags); >> - if (err) { >> - VLOG_ERR("vhost-user socket device setup failure for socket %s\n", >> - dev->vhost_id); >> - } else { >> + err = dpdk_attach_vhost_pmd(dev, 0); >> + >> + if (!err) { >> fatal_signal_add_file_to_unlink(dev->vhost_id); >> VLOG_INFO("Socket %s created for vhost-user port %s\n", >> dev->vhost_id, name); >> } >> - err = netdev_dpdk_init(netdev, -1, DPDK_DEV_VHOST); >> + err = netdev_dpdk_init(netdev, dev->port_id, DPDK_DEV_VHOST); > > Someone must detach port on failure. > >> ovs_mutex_unlock(&dpdk_mutex); >> return err; >> @@ -964,13 +1134,10 @@ netdev_dpdk_construct(struct netdev *netdev) >> } >> >> static void >> -netdev_dpdk_destruct(struct netdev *netdev) >> +dpdk_destruct_helper(struct netdev_dpdk *dev) >> + OVS_REQUIRES(dpdk_mutex) >> + OVS_REQUIRES(dev->mutex) >> { >> - struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> - >> - ovs_mutex_lock(&dpdk_mutex); >> - ovs_mutex_lock(&dev->mutex); >> - >> rte_eth_dev_stop(dev->port_id); >> free(ovsrcu_get_protected(struct ingress_policer *, >> &dev->ingress_policer)); >> @@ -978,61 +1145,43 @@ netdev_dpdk_destruct(struct netdev *netdev) >> rte_free(dev->tx_q); >> ovs_list_remove(&dev->list_node); >> dpdk_mp_put(dev->dpdk_mp); >> - >> - ovs_mutex_unlock(&dev->mutex); >> - ovs_mutex_unlock(&dpdk_mutex); >> } >> >> -/* rte_vhost_driver_unregister() can call back destroy_device(), which will >> - * try to acquire 'dpdk_mutex' and possibly 'dev->mutex'. To avoid a >> - * deadlock, none of the mutexes must be held while calling this function. >> */ >> -static int >> -dpdk_vhost_driver_unregister(struct netdev_dpdk *dev OVS_UNUSED, >> - char *vhost_id) >> - OVS_EXCLUDED(dpdk_mutex) >> - OVS_EXCLUDED(dev->mutex) >> +static void >> +netdev_dpdk_destruct(struct netdev *netdev) >> { >> - return rte_vhost_driver_unregister(vhost_id); >> + struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> + >> + ovs_mutex_lock(&dpdk_mutex); >> + ovs_mutex_lock(&dev->mutex); >> + >> + dpdk_destruct_helper(dev); >> + >> + ovs_mutex_unlock(&dev->mutex); >> + ovs_mutex_unlock(&dpdk_mutex); >> } >> >> static void >> netdev_dpdk_vhost_destruct(struct netdev *netdev) >> { >> struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> - char *vhost_id; >> >> ovs_mutex_lock(&dpdk_mutex); >> ovs_mutex_lock(&dev->mutex); >> >> - /* Guest becomes an orphan if still attached. */ >> - if (netdev_dpdk_get_vid(dev) >= 0 >> - && !(dev->vhost_driver_flags & RTE_VHOST_USER_CLIENT)) { >> - VLOG_ERR("Removing port '%s' while vhost device still attached.", >> - netdev->name); >> - VLOG_ERR("To restore connectivity after re-adding of port, VM on " >> - "socket '%s' must be restarted.", dev->vhost_id); >> + if (rte_eth_dev_detach(dev->port_id, dev->vhost_id)) { >> + VLOG_ERR("Error removing vhost device %s", dev->vhost_id); >> + } else { >> + if (!(dev->flags & RTE_VHOST_USER_CLIENT)) { > > Flag is unset if port not attached. > >> + fatal_signal_remove_file_to_unlink(dev->vhost_id); >> + } >> } >> + set_vhost_drv_id(dev->vhost_pmd_id, 0); >> >> - free(ovsrcu_get_protected(struct ingress_policer *, >> - &dev->ingress_policer)); >> - >> - rte_free(dev->tx_q); >> - ovs_list_remove(&dev->list_node); >> - dpdk_mp_put(dev->dpdk_mp); >> - >> - vhost_id = xstrdup(dev->vhost_id); >> + dpdk_destruct_helper(dev); >> >> ovs_mutex_unlock(&dev->mutex); >> ovs_mutex_unlock(&dpdk_mutex); >> - >> - if (dpdk_vhost_driver_unregister(dev, vhost_id)) { >> - VLOG_ERR("%s: Unable to unregister vhost driver for socket '%s'.\n", >> - netdev->name, vhost_id); >> - } else if (!(dev->vhost_driver_flags & RTE_VHOST_USER_CLIENT)) { >> - /* OVS server mode - remove this socket from list for deletion */ >> - fatal_signal_remove_file_to_unlink(vhost_id); >> - } >> - free(vhost_id); >> } >> >> static void >> @@ -1054,12 +1203,16 @@ netdev_dpdk_get_config(const struct netdev *netdev, >> struct smap *args) >> smap_add_format(args, "configured_rx_queues", "%d", netdev->n_rxq); >> smap_add_format(args, "requested_tx_queues", "%d", >> dev->requested_n_txq); >> smap_add_format(args, "configured_tx_queues", "%d", netdev->n_txq); >> - smap_add_format(args, "requested_rxq_descriptors", "%d", >> - dev->requested_rxq_size); >> - smap_add_format(args, "configured_rxq_descriptors", "%d", >> dev->rxq_size); >> - smap_add_format(args, "requested_txq_descriptors", "%d", >> - dev->requested_txq_size); >> - smap_add_format(args, "configured_txq_descriptors", "%d", >> dev->txq_size); >> + if (dev->type == DPDK_DEV_ETH) { >> + smap_add_format(args, "requested_rxq_descriptors", "%d", >> + dev->requested_rxq_size); >> + smap_add_format(args, "configured_rxq_descriptors", "%d", >> + dev->rxq_size); >> + smap_add_format(args, "requested_txq_descriptors", "%d", >> + dev->requested_txq_size); >> + smap_add_format(args, "configured_txq_descriptors", "%d", >> + dev->txq_size); >> + } >> smap_add_format(args, "mtu", "%d", dev->mtu); >> ovs_mutex_unlock(&dev->mutex); >> >> @@ -1320,119 +1473,8 @@ ingress_policer_run(struct ingress_policer *policer, >> struct rte_mbuf **pkts, >> return cnt; >> } >> >> -static bool >> -is_vhost_running(struct netdev_dpdk *dev) >> -{ >> - return (netdev_dpdk_get_vid(dev) >= 0 && dev->vhost_reconfigured); >> -} >> - >> -static inline void >> -netdev_dpdk_vhost_update_rx_size_counters(struct netdev_stats *stats, >> - unsigned int packet_size) >> -{ >> - /* Hard-coded search for the size bucket. */ >> - if (packet_size < 256) { >> - if (packet_size >= 128) { >> - stats->rx_128_to_255_packets++; >> - } else if (packet_size <= 64) { >> - stats->rx_1_to_64_packets++; >> - } else { >> - stats->rx_65_to_127_packets++; >> - } >> - } else { >> - if (packet_size >= 1523) { >> - stats->rx_1523_to_max_packets++; >> - } else if (packet_size >= 1024) { >> - stats->rx_1024_to_1522_packets++; >> - } else if (packet_size < 512) { >> - stats->rx_256_to_511_packets++; >> - } else { >> - stats->rx_512_to_1023_packets++; >> - } >> - } >> -} >> - >> -static inline void >> -netdev_dpdk_vhost_update_rx_counters(struct netdev_stats *stats, >> - struct dp_packet **packets, int count, >> - int dropped) >> -{ >> - int i; >> - unsigned int packet_size; >> - struct dp_packet *packet; >> - >> - stats->rx_packets += count; >> - stats->rx_dropped += dropped; >> - for (i = 0; i < count; i++) { >> - packet = packets[i]; >> - packet_size = dp_packet_size(packet); >> - >> - if (OVS_UNLIKELY(packet_size < ETH_HEADER_LEN)) { >> - /* This only protects the following multicast counting from >> - * too short packets, but it does not stop the packet from >> - * further processing. */ >> - stats->rx_errors++; >> - stats->rx_length_errors++; >> - continue; >> - } >> - >> - netdev_dpdk_vhost_update_rx_size_counters(stats, packet_size); >> - >> - struct eth_header *eh = (struct eth_header *) >> dp_packet_data(packet); >> - if (OVS_UNLIKELY(eth_addr_is_multicast(eh->eth_dst))) { >> - stats->multicast++; >> - } >> - >> - stats->rx_bytes += packet_size; >> - } >> -} >> - >> -/* >> - * The receive path for the vhost port is the TX path out from guest. >> - */ >> -static int >> -netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq, >> - struct dp_packet_batch *batch) >> -{ >> - struct netdev_dpdk *dev = netdev_dpdk_cast(rxq->netdev); >> - int qid = rxq->queue_id; >> - struct ingress_policer *policer = netdev_dpdk_get_ingress_policer(dev); >> - uint16_t nb_rx = 0; >> - uint16_t dropped = 0; >> - >> - if (OVS_UNLIKELY(!is_vhost_running(dev) >> - || !(dev->flags & NETDEV_UP))) { >> - return EAGAIN; >> - } >> - >> - nb_rx = rte_vhost_dequeue_burst(netdev_dpdk_get_vid(dev), >> - qid * VIRTIO_QNUM + VIRTIO_TXQ, >> - dev->dpdk_mp->mp, >> - (struct rte_mbuf **) batch->packets, >> - NETDEV_MAX_BURST); >> - if (!nb_rx) { >> - return EAGAIN; >> - } >> - >> - if (policer) { >> - dropped = nb_rx; >> - nb_rx = ingress_policer_run(policer, >> - (struct rte_mbuf **) batch->packets, >> - nb_rx); >> - dropped -= nb_rx; >> - } >> - >> - rte_spinlock_lock(&dev->stats_lock); >> - netdev_dpdk_vhost_update_rx_counters(&dev->stats, batch->packets, >> - nb_rx, dropped); >> - rte_spinlock_unlock(&dev->stats_lock); >> - >> - batch->count = (int) nb_rx; >> - return 0; >> -} >> - >> -static int >> -netdev_dpdk_rxq_recv(struct netdev_rxq *rxq, struct dp_packet_batch *batch) >> +static inline int >> +dpdk_rxq_recv(struct netdev_rxq *rxq, struct dp_packet_batch *batch) >> { >> struct netdev_rxq_dpdk *rx = netdev_rxq_dpdk_cast(rxq); >> struct netdev_dpdk *dev = netdev_dpdk_cast(rxq->netdev); >> @@ -1467,6 +1509,30 @@ netdev_dpdk_rxq_recv(struct netdev_rxq *rxq, struct >> dp_packet_batch *batch) >> return 0; >> } >> >> +static int >> +netdev_dpdk_rxq_recv(struct netdev_rxq *rxq, struct dp_packet_batch *batch) >> +{ >> + return dpdk_rxq_recv(rxq, batch); >> +} >> + >> +static int >> +netdev_dpdk_vhost_client_rxq_recv(struct netdev_rxq *rxq, >> + struct dp_packet_batch *batch) >> +{ >> + struct netdev_rxq_dpdk *rx = netdev_rxq_dpdk_cast(rxq); >> + >> + if (rte_eth_dev_is_valid_port(rx->port_id)) { >> + return dpdk_rxq_recv(rxq, batch); >> + } else { >> + struct netdev_dpdk *dev = netdev_dpdk_cast(rxq->netdev); >> + >> + rte_spinlock_lock(&dev->stats_lock); >> + dev->stats.rx_dropped += batch->count; >> + rte_spinlock_unlock(&dev->stats_lock); >> + return 0; >> + } >> +} >> + >> static inline int >> netdev_dpdk_qos_run(struct netdev_dpdk *dev, struct rte_mbuf **pkts, >> int cnt) >> @@ -1508,80 +1574,6 @@ netdev_dpdk_filter_packet_len(struct netdev_dpdk >> *dev, struct rte_mbuf **pkts, >> return cnt; >> } >> >> -static inline void >> -netdev_dpdk_vhost_update_tx_counters(struct netdev_stats *stats, >> - struct dp_packet **packets, >> - int attempted, >> - int dropped) >> -{ >> - int i; >> - int sent = attempted - dropped; >> - >> - stats->tx_packets += sent; >> - stats->tx_dropped += dropped; >> - >> - for (i = 0; i < sent; i++) { >> - stats->tx_bytes += dp_packet_size(packets[i]); >> - } >> -} >> - >> -static void >> -__netdev_dpdk_vhost_send(struct netdev *netdev, int qid, >> - struct dp_packet **pkts, int cnt) >> -{ >> - struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> - struct rte_mbuf **cur_pkts = (struct rte_mbuf **) pkts; >> - unsigned int total_pkts = cnt; >> - unsigned int dropped = 0; >> - int i, retries = 0; >> - >> - qid = dev->tx_q[qid % netdev->n_txq].map; >> - >> - if (OVS_UNLIKELY(!is_vhost_running(dev) || qid < 0 >> - || !(dev->flags & NETDEV_UP))) { >> - rte_spinlock_lock(&dev->stats_lock); >> - dev->stats.tx_dropped+= cnt; >> - rte_spinlock_unlock(&dev->stats_lock); >> - goto out; >> - } >> - >> - rte_spinlock_lock(&dev->tx_q[qid].tx_lock); >> - >> - cnt = netdev_dpdk_filter_packet_len(dev, cur_pkts, cnt); >> - /* Check has QoS has been configured for the netdev */ >> - cnt = netdev_dpdk_qos_run(dev, cur_pkts, cnt); >> - dropped = total_pkts - cnt; >> - >> - do { >> - int vhost_qid = qid * VIRTIO_QNUM + VIRTIO_RXQ; >> - unsigned int tx_pkts; >> - >> - tx_pkts = rte_vhost_enqueue_burst(netdev_dpdk_get_vid(dev), >> - vhost_qid, cur_pkts, cnt); >> - if (OVS_LIKELY(tx_pkts)) { >> - /* Packets have been sent.*/ >> - cnt -= tx_pkts; >> - /* Prepare for possible retry.*/ >> - cur_pkts = &cur_pkts[tx_pkts]; >> - } else { >> - /* No packets sent - do not retry.*/ >> - break; >> - } >> - } while (cnt && (retries++ <= VHOST_ENQ_RETRY_NUM)); >> - >> - rte_spinlock_unlock(&dev->tx_q[qid].tx_lock); >> - >> - rte_spinlock_lock(&dev->stats_lock); >> - netdev_dpdk_vhost_update_tx_counters(&dev->stats, pkts, total_pkts, >> - cnt + dropped); >> - rte_spinlock_unlock(&dev->stats_lock); >> - >> -out: >> - for (i = 0; i < total_pkts - dropped; i++) { >> - dp_packet_delete(pkts[i]); >> - } >> -} >> - >> /* Tx function. Transmit packets indefinitely */ >> static void >> dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet_batch >> *batch) >> @@ -1629,18 +1621,13 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, >> struct dp_packet_batch *batch) >> newcnt++; >> } >> >> - if (dev->type == DPDK_DEV_VHOST) { >> - __netdev_dpdk_vhost_send(netdev, qid, (struct dp_packet **) pkts, >> - newcnt); >> - } else { >> - unsigned int qos_pkts = newcnt; >> + unsigned int qos_pkts = newcnt; >> >> - /* Check if QoS has been configured for this netdev. */ >> - newcnt = netdev_dpdk_qos_run(dev, pkts, newcnt); >> + /* Check if QoS has been configured for this netdev. */ >> + newcnt = netdev_dpdk_qos_run(dev, pkts, newcnt); >> >> - dropped += qos_pkts - newcnt; >> - dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, newcnt); >> - } >> + dropped += qos_pkts - newcnt; >> + dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, newcnt); >> >> if (OVS_UNLIKELY(dropped)) { >> rte_spinlock_lock(&dev->stats_lock); >> @@ -1649,32 +1636,10 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, >> struct dp_packet_batch *batch) >> } >> } >> >> -static int >> -netdev_dpdk_vhost_send(struct netdev *netdev, int qid, >> - struct dp_packet_batch *batch, >> - bool may_steal, bool concurrent_txq OVS_UNUSED) >> -{ >> - >> - if (OVS_UNLIKELY(!may_steal || batch->packets[0]->source != >> DPBUF_DPDK)) { >> - dpdk_do_tx_copy(netdev, qid, batch); >> - dp_packet_delete_batch(batch, may_steal); >> - } else { >> - dp_packet_batch_apply_cutlen(batch); >> - __netdev_dpdk_vhost_send(netdev, qid, batch->packets, batch->count); >> - } >> - return 0; >> -} >> - >> static inline void >> netdev_dpdk_send__(struct netdev_dpdk *dev, int qid, >> - struct dp_packet_batch *batch, bool may_steal, >> - bool concurrent_txq) >> + struct dp_packet_batch *batch, bool may_steal) >> { >> - if (OVS_UNLIKELY(concurrent_txq)) { >> - qid = qid % dev->up.n_txq; >> - rte_spinlock_lock(&dev->tx_q[qid].tx_lock); >> - } >> - >> if (OVS_UNLIKELY(!may_steal || >> batch->packets[0]->source != DPBUF_DPDK)) { >> struct netdev *netdev = &dev->up; >> @@ -1700,20 +1665,50 @@ netdev_dpdk_send__(struct netdev_dpdk *dev, int qid, >> rte_spinlock_unlock(&dev->stats_lock); >> } >> } >> +} >> + >> +static int >> +netdev_dpdk_eth_send(struct netdev *netdev, int qid, >> + struct dp_packet_batch *batch, bool may_steal, >> + bool concurrent_txq) >> +{ >> + struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> + >> + if (OVS_UNLIKELY(concurrent_txq)) { >> + qid = qid % dev->up.n_txq; >> + rte_spinlock_lock(&dev->tx_q[qid].tx_lock); >> + } >> + >> + netdev_dpdk_send__(dev, qid, batch, may_steal); >> >> if (OVS_UNLIKELY(concurrent_txq)) { >> rte_spinlock_unlock(&dev->tx_q[qid].tx_lock); >> } >> + >> + return 0; >> } >> >> static int >> -netdev_dpdk_eth_send(struct netdev *netdev, int qid, >> - struct dp_packet_batch *batch, bool may_steal, >> - bool concurrent_txq) >> +netdev_dpdk_vhost_send(struct netdev *netdev, int qid, >> + struct dp_packet_batch *batch, bool may_steal, >> + bool concurrent_txq OVS_UNUSED) >> { >> struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> >> - netdev_dpdk_send__(dev, qid, batch, may_steal, concurrent_txq); >> + qid = dev->tx_q[qid % netdev->n_txq].map; >> + if (qid == -1) { >> + rte_spinlock_lock(&dev->stats_lock); >> + dev->stats.tx_dropped+= batch->count; >> + rte_spinlock_unlock(&dev->stats_lock); >> + if (may_steal) { >> + dp_packet_delete_batch(batch, may_steal); >> + } >> + } else { >> + rte_spinlock_lock(&dev->tx_q[qid].tx_lock); >> + netdev_dpdk_send__(dev, qid, batch, may_steal); >> + rte_spinlock_unlock(&dev->tx_q[qid].tx_lock); >> + } >> + >> return 0; >> } >> >> @@ -1780,41 +1775,6 @@ netdev_dpdk_set_mtu(struct netdev *netdev, int mtu) >> static int >> netdev_dpdk_get_carrier(const struct netdev *netdev, bool *carrier); >> >> -static int >> -netdev_dpdk_vhost_get_stats(const struct netdev *netdev, >> - struct netdev_stats *stats) >> -{ >> - struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> - >> - ovs_mutex_lock(&dev->mutex); >> - >> - rte_spinlock_lock(&dev->stats_lock); >> - /* Supported Stats */ >> - stats->rx_packets += dev->stats.rx_packets; >> - stats->tx_packets += dev->stats.tx_packets; >> - stats->rx_dropped = dev->stats.rx_dropped; >> - stats->tx_dropped += dev->stats.tx_dropped; >> - stats->multicast = dev->stats.multicast; >> - stats->rx_bytes = dev->stats.rx_bytes; >> - stats->tx_bytes = dev->stats.tx_bytes; >> - stats->rx_errors = dev->stats.rx_errors; >> - stats->rx_length_errors = dev->stats.rx_length_errors; >> - >> - stats->rx_1_to_64_packets = dev->stats.rx_1_to_64_packets; >> - stats->rx_65_to_127_packets = dev->stats.rx_65_to_127_packets; >> - stats->rx_128_to_255_packets = dev->stats.rx_128_to_255_packets; >> - stats->rx_256_to_511_packets = dev->stats.rx_256_to_511_packets; >> - stats->rx_512_to_1023_packets = dev->stats.rx_512_to_1023_packets; >> - stats->rx_1024_to_1522_packets = dev->stats.rx_1024_to_1522_packets; >> - stats->rx_1523_to_max_packets = dev->stats.rx_1523_to_max_packets; >> - >> - rte_spinlock_unlock(&dev->stats_lock); >> - >> - ovs_mutex_unlock(&dev->mutex); >> - >> - return 0; >> -} >> - >> static void >> netdev_dpdk_convert_xstats(struct netdev_stats *stats, >> const struct rte_eth_xstat *xstats, >> @@ -1858,6 +1818,8 @@ netdev_dpdk_convert_xstats(struct netdev_stats *stats, >> stats->tx_broadcast_packets = xstats[i].value; >> } else if (strcmp(XSTAT_RX_UNDERSIZED_ERRORS, names[i].name) == 0) { >> stats->rx_undersized_errors = xstats[i].value; >> + } else if (strcmp(XSTAT_RX_UNDERSIZE_PACKETS, names[i].name) == 0) { >> + stats->rx_undersized_errors = xstats[i].value; >> } else if (strcmp(XSTAT_RX_FRAGMENTED_ERRORS, names[i].name) == 0) { >> stats->rx_fragmented_errors = xstats[i].value; >> } else if (strcmp(XSTAT_RX_JABBER_ERRORS, names[i].name) == 0) { >> @@ -1880,62 +1842,66 @@ netdev_dpdk_get_stats(const struct netdev *netdev, >> struct netdev_stats *stats) >> struct rte_eth_xstat_name *rte_xstats_names = NULL; >> int rte_xstats_len, rte_xstats_new_len, rte_xstats_ret; >> >> - if (rte_eth_stats_get(dev->port_id, &rte_stats)) { >> - VLOG_ERR("Can't get ETH statistics for port: %i.", dev->port_id); >> - ovs_mutex_unlock(&dev->mutex); >> - return EPROTO; >> - } >> + if (rte_eth_dev_is_valid_port(dev->port_id)) { >> + if (rte_eth_stats_get(dev->port_id, &rte_stats)) { >> + VLOG_ERR("Can't get ETH statistics for port: %i.", >> dev->port_id); >> + ovs_mutex_unlock(&dev->mutex); >> + return EPROTO; >> + } >> >> - /* Get length of statistics */ >> - rte_xstats_len = rte_eth_xstats_get_names(dev->port_id, NULL, 0); >> - if (rte_xstats_len < 0) { >> - VLOG_WARN("Cannot get XSTATS values for port: %i", dev->port_id); >> - goto out; >> - } >> - /* Reserve memory for xstats names and values */ >> - rte_xstats_names = xcalloc(rte_xstats_len, sizeof *rte_xstats_names); >> - rte_xstats = xcalloc(rte_xstats_len, sizeof *rte_xstats); >> + /* Get length of statistics */ >> + rte_xstats_len = rte_eth_xstats_get_names(dev->port_id, NULL, 0); >> + if (rte_xstats_len < 0) { >> + VLOG_WARN("Cannot get XSTATS values for port: %i", >> dev->port_id); >> + goto out; >> + } >> + /* Reserve memory for xstats names and values */ >> + rte_xstats_names = xcalloc(rte_xstats_len, sizeof >> *rte_xstats_names); >> + rte_xstats = xcalloc(rte_xstats_len, sizeof *rte_xstats); >> + >> + /* Retreive xstats names */ >> + rte_xstats_new_len = rte_eth_xstats_get_names(dev->port_id, >> + rte_xstats_names, >> + rte_xstats_len); >> + if (rte_xstats_new_len != rte_xstats_len) { >> + VLOG_WARN("Cannot get XSTATS names for port: %i.", >> dev->port_id); >> + goto out; >> + } >> + /* Retreive xstats values */ >> + memset(rte_xstats, 0xff, sizeof *rte_xstats * rte_xstats_len); >> + rte_xstats_ret = rte_eth_xstats_get(dev->port_id, rte_xstats, >> + rte_xstats_len); >> + if (rte_xstats_ret > 0 && rte_xstats_ret <= rte_xstats_len) { >> + netdev_dpdk_convert_xstats(stats, rte_xstats, rte_xstats_names, >> + rte_xstats_len); >> + } else { >> + VLOG_WARN("Cannot get XSTATS values for port: %i.", >> dev->port_id); >> + } >> >> - /* Retreive xstats names */ >> - rte_xstats_new_len = rte_eth_xstats_get_names(dev->port_id, >> - rte_xstats_names, >> - rte_xstats_len); >> - if (rte_xstats_new_len != rte_xstats_len) { >> - VLOG_WARN("Cannot get XSTATS names for port: %i.", dev->port_id); >> - goto out; >> - } >> - /* Retreive xstats values */ >> - memset(rte_xstats, 0xff, sizeof *rte_xstats * rte_xstats_len); >> - rte_xstats_ret = rte_eth_xstats_get(dev->port_id, rte_xstats, >> - rte_xstats_len); >> - if (rte_xstats_ret > 0 && rte_xstats_ret <= rte_xstats_len) { >> - netdev_dpdk_convert_xstats(stats, rte_xstats, rte_xstats_names, >> - rte_xstats_len); >> - } else { >> - VLOG_WARN("Cannot get XSTATS values for port: %i.", dev->port_id); >> - } >> + out: >> + free(rte_xstats); >> + free(rte_xstats_names); >> >> -out: >> - free(rte_xstats); >> - free(rte_xstats_names); >> - >> - stats->rx_packets = rte_stats.ipackets; >> - stats->tx_packets = rte_stats.opackets; >> - stats->rx_bytes = rte_stats.ibytes; >> - stats->tx_bytes = rte_stats.obytes; >> - /* DPDK counts imissed as errors, but count them here as dropped >> instead */ >> - stats->rx_errors = rte_stats.ierrors - rte_stats.imissed; >> - stats->tx_errors = rte_stats.oerrors; >> - >> - rte_spinlock_lock(&dev->stats_lock); >> - stats->tx_dropped = dev->stats.tx_dropped; >> - stats->rx_dropped = dev->stats.rx_dropped; >> - rte_spinlock_unlock(&dev->stats_lock); >> - >> - /* These are the available DPDK counters for packets not received due to >> - * local resource constraints in DPDK and NIC respectively. */ >> - stats->rx_dropped += rte_stats.rx_nombuf + rte_stats.imissed; >> - stats->rx_missed_errors = rte_stats.imissed; >> + stats->rx_packets = rte_stats.ipackets; >> + stats->tx_packets = rte_stats.opackets; >> + stats->rx_bytes = rte_stats.ibytes; >> + stats->tx_bytes = rte_stats.obytes; >> + >> + /* DPDK counts imissed as errors, but count them here as dropped >> + * instead */ >> + stats->rx_errors = rte_stats.ierrors - rte_stats.imissed; >> + stats->tx_errors = rte_stats.oerrors; >> + >> + rte_spinlock_lock(&dev->stats_lock); >> + stats->tx_dropped = dev->stats.tx_dropped; >> + stats->rx_dropped = dev->stats.rx_dropped; >> + rte_spinlock_unlock(&dev->stats_lock); >> + >> + /* These are the available DPDK counters for packets not received >> due >> + * to local resource constraints in DPDK and NIC respectively. */ >> + stats->rx_dropped += rte_stats.rx_nombuf + rte_stats.imissed; >> + stats->rx_missed_errors = rte_stats.imissed; >> + } >> >> ovs_mutex_unlock(&dev->mutex); >> >> @@ -2088,24 +2054,6 @@ netdev_dpdk_get_carrier(const struct netdev *netdev, >> bool *carrier) >> return 0; >> } >> >> -static int >> -netdev_dpdk_vhost_get_carrier(const struct netdev *netdev, bool *carrier) >> -{ >> - struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> - >> - ovs_mutex_lock(&dev->mutex); >> - >> - if (is_vhost_running(dev)) { >> - *carrier = 1; >> - } else { >> - *carrier = 0; >> - } >> - >> - ovs_mutex_unlock(&dev->mutex); >> - >> - return 0; >> -} >> - >> static long long int >> netdev_dpdk_get_carrier_resets(const struct netdev *netdev) >> { >> @@ -2161,12 +2109,10 @@ netdev_dpdk_update_flags__(struct netdev_dpdk *dev, >> rte_eth_dev_stop(dev->port_id); >> } >> } else { >> - /* If DPDK_DEV_VHOST device's NETDEV_UP flag was changed and vhost >> is >> - * running then change netdev's change_seq to trigger link state >> - * update. */ >> + /* If DPDK_DEV_VHOST device's NETDEV_UP flag was changed then change >> + * netdev's change_seq to trigger link state update. */ >> >> - if ((NETDEV_UP & ((*old_flagsp ^ on) | (*old_flagsp ^ off))) >> - && is_vhost_running(dev)) { >> + if ((NETDEV_UP & ((*old_flagsp ^ on) | (*old_flagsp ^ off)))) { >> netdev_change_seq_changed(&dev->up); >> >> /* Clear statistics if device is getting up. */ >> @@ -2224,11 +2170,17 @@ netdev_dpdk_get_status(const struct netdev *netdev, >> struct smap *args) >> smap_add_format(args, "max_vfs", "%u", dev_info.max_vfs); >> smap_add_format(args, "max_vmdq_pools", "%u", dev_info.max_vmdq_pools); >> >> - if (dev_info.pci_dev) { >> - smap_add_format(args, "pci-vendor_id", "0x%u", >> - dev_info.pci_dev->id.vendor_id); >> - smap_add_format(args, "pci-device_id", "0x%x", >> - dev_info.pci_dev->id.device_id); >> + if (dev->type == DPDK_DEV_ETH) { >> + smap_add_format(args, "max_hash_mac_addrs", "%u", >> + dev_info.max_hash_mac_addrs); >> + smap_add_format(args, "max_vfs", "%u", dev_info.max_vfs); >> + smap_add_format(args, "max_vmdq_pools", "%u", >> dev_info.max_vmdq_pools); >> + if (dev_info.pci_dev) { >> + smap_add_format(args, "pci-vendor_id", "0x%u", >> + dev_info.pci_dev->id.vendor_id); >> + smap_add_format(args, "pci-device_id", "0x%x", >> + dev_info.pci_dev->id.device_id); >> + } >> } >> >> return 0; >> @@ -2264,7 +2216,7 @@ netdev_dpdk_set_admin_state(struct unixctl_conn *conn, >> int argc, >> >> if (argc > 2) { >> struct netdev *netdev = netdev_from_name(argv[1]); >> - if (netdev && is_dpdk_class(netdev->netdev_class)) { >> + if (netdev && is_dpdk_eth_class(netdev->netdev_class)) { >> struct netdev_dpdk *dpdk_dev = netdev_dpdk_cast(netdev); >> >> ovs_mutex_lock(&dpdk_dev->mutex); >> @@ -2292,22 +2244,6 @@ netdev_dpdk_set_admin_state(struct unixctl_conn >> *conn, int argc, >> } >> >> /* >> - * Set virtqueue flags so that we do not receive interrupts. >> - */ >> -static void >> -set_irq_status(int vid) >> -{ >> - uint32_t i; >> - uint64_t idx; >> - >> - for (i = 0; i < rte_vhost_get_queue_num(vid); i++) { >> - idx = i * VIRTIO_QNUM; >> - rte_vhost_enable_guest_notification(vid, idx + VIRTIO_RXQ, 0); >> - rte_vhost_enable_guest_notification(vid, idx + VIRTIO_TXQ, 0); >> - } >> -} >> - >> -/* >> * Fixes mapping for vhost-user tx queues. Must be called after each >> * enabling/disabling of queues and n_txq modifications. >> */ >> @@ -2348,73 +2284,6 @@ netdev_dpdk_remap_txqs(struct netdev_dpdk *dev) >> free(enabled_queues); >> } >> >> -/* >> - * A new virtio-net device is added to a vhost port. >> - */ >> -static int >> -new_device(int vid) >> -{ >> - struct netdev_dpdk *dev; >> - bool exists = false; >> - int newnode = 0; >> - char ifname[IF_NAME_SZ]; >> - >> - rte_vhost_get_ifname(vid, ifname, sizeof ifname); >> - >> - ovs_mutex_lock(&dpdk_mutex); >> - /* Add device to the vhost port with the same name as that passed down. >> */ >> - LIST_FOR_EACH(dev, list_node, &dpdk_list) { >> - ovs_mutex_lock(&dev->mutex); >> - if (strncmp(ifname, dev->vhost_id, IF_NAME_SZ) == 0) { >> - uint32_t qp_num = rte_vhost_get_queue_num(vid); >> - >> - /* Get NUMA information */ >> - newnode = rte_vhost_get_numa_node(vid); >> - if (newnode == -1) { >> -#ifdef VHOST_NUMA >> - VLOG_INFO("Error getting NUMA info for vHost Device '%s'", >> - ifname); >> -#endif >> - newnode = dev->socket_id; >> - } >> - >> - if (dev->requested_n_txq != qp_num >> - || dev->requested_n_rxq != qp_num >> - || dev->requested_socket_id != newnode) { >> - dev->requested_socket_id = newnode; >> - dev->requested_n_rxq = qp_num; >> - dev->requested_n_txq = qp_num; >> - netdev_request_reconfigure(&dev->up); >> - } else { >> - /* Reconfiguration not required. */ >> - dev->vhost_reconfigured = true; >> - } >> - >> - ovsrcu_index_set(&dev->vid, vid); >> - exists = true; >> - >> - /* Disable notifications. */ >> - set_irq_status(vid); >> - netdev_change_seq_changed(&dev->up); >> - ovs_mutex_unlock(&dev->mutex); >> - break; >> - } >> - ovs_mutex_unlock(&dev->mutex); >> - } >> - ovs_mutex_unlock(&dpdk_mutex); >> - >> - if (!exists) { >> - VLOG_INFO("vHost Device '%s' can't be added - name not found", >> ifname); >> - >> - return -1; >> - } >> - >> - VLOG_INFO("vHost Device '%s' has been added on numa node %i", >> - ifname, newnode); >> - >> - return 0; >> -} >> - >> /* Clears mapping for all available queues of vhost interface. */ >> static void >> netdev_dpdk_txq_map_clear(struct netdev_dpdk *dev) >> @@ -2427,133 +2296,12 @@ netdev_dpdk_txq_map_clear(struct netdev_dpdk *dev) >> } >> } >> >> -/* >> - * Remove a virtio-net device from the specific vhost port. Use dev->remove >> - * flag to stop any more packets from being sent or received to/from a VM >> and >> - * ensure all currently queued packets have been sent/received before >> removing >> - * the device. >> - */ >> -static void >> -destroy_device(int vid) >> -{ >> - struct netdev_dpdk *dev; >> - bool exists = false; >> - char ifname[IF_NAME_SZ]; >> - >> - rte_vhost_get_ifname(vid, ifname, sizeof ifname); >> - >> - ovs_mutex_lock(&dpdk_mutex); >> - LIST_FOR_EACH (dev, list_node, &dpdk_list) { >> - if (netdev_dpdk_get_vid(dev) == vid) { >> - >> - ovs_mutex_lock(&dev->mutex); >> - dev->vhost_reconfigured = false; >> - ovsrcu_index_set(&dev->vid, -1); >> - netdev_dpdk_txq_map_clear(dev); >> - >> - netdev_change_seq_changed(&dev->up); >> - ovs_mutex_unlock(&dev->mutex); >> - exists = true; >> - break; >> - } >> - } >> - >> - ovs_mutex_unlock(&dpdk_mutex); >> - >> - if (exists) { >> - /* >> - * Wait for other threads to quiesce after setting the 'virtio_dev' >> - * to NULL, before returning. >> - */ >> - ovsrcu_synchronize(); >> - /* >> - * As call to ovsrcu_synchronize() will end the quiescent state, >> - * put thread back into quiescent state before returning. >> - */ >> - ovsrcu_quiesce_start(); >> - VLOG_INFO("vHost Device '%s' has been removed", ifname); >> - } else { >> - VLOG_INFO("vHost Device '%s' not found", ifname); >> - } >> -} >> - >> -static int >> -vring_state_changed(int vid, uint16_t queue_id, int enable) >> -{ >> - struct netdev_dpdk *dev; >> - bool exists = false; >> - int qid = queue_id / VIRTIO_QNUM; >> - char ifname[IF_NAME_SZ]; >> - >> - rte_vhost_get_ifname(vid, ifname, sizeof ifname); >> - >> - if (queue_id % VIRTIO_QNUM == VIRTIO_TXQ) { >> - return 0; >> - } >> - >> - ovs_mutex_lock(&dpdk_mutex); >> - LIST_FOR_EACH (dev, list_node, &dpdk_list) { >> - ovs_mutex_lock(&dev->mutex); >> - if (strncmp(ifname, dev->vhost_id, IF_NAME_SZ) == 0) { >> - if (enable) { >> - dev->tx_q[qid].map = qid; >> - } else { >> - dev->tx_q[qid].map = OVS_VHOST_QUEUE_DISABLED; >> - } >> - netdev_dpdk_remap_txqs(dev); >> - exists = true; >> - ovs_mutex_unlock(&dev->mutex); >> - break; >> - } >> - ovs_mutex_unlock(&dev->mutex); >> - } >> - ovs_mutex_unlock(&dpdk_mutex); >> - >> - if (exists) { >> - VLOG_INFO("State of queue %d ( tx_qid %d ) of vhost device '%s'" >> - "changed to \'%s\'", queue_id, qid, ifname, >> - (enable == 1) ? "enabled" : "disabled"); >> - } else { >> - VLOG_INFO("vHost Device '%s' not found", ifname); >> - return -1; >> - } >> - >> - return 0; >> -} >> - >> -int >> -netdev_dpdk_get_vid(const struct netdev_dpdk *dev) >> -{ >> - return ovsrcu_index_get(&dev->vid); >> -} >> - >> struct ingress_policer * >> netdev_dpdk_get_ingress_policer(const struct netdev_dpdk *dev) >> { >> return ovsrcu_get(struct ingress_policer *, &dev->ingress_policer); >> } >> >> -/* >> - * These callbacks allow virtio-net devices to be added to vhost ports when >> - * configuration has been fully complete. >> - */ >> -static const struct virtio_net_device_ops virtio_net_device_ops = >> -{ >> - .new_device = new_device, >> - .destroy_device = destroy_device, >> - .vring_state_changed = vring_state_changed >> -}; >> - >> -static void * >> -start_vhost_loop(void *dummy OVS_UNUSED) >> -{ >> - pthread_detach(pthread_self()); >> - /* Put the vhost thread into quiescent state. */ >> - ovsrcu_quiesce_start(); >> - rte_vhost_driver_session_start(); >> - return NULL; >> -} >> - >> static int >> netdev_dpdk_class_init(void) >> { >> @@ -2576,19 +2324,9 @@ netdev_dpdk_class_init(void) >> static int >> netdev_dpdk_vhost_class_init(void) >> { >> - static struct ovsthread_once once = OVSTHREAD_ONCE_INITIALIZER; >> - >> - /* This function can be called for different classes. The >> initialization >> - * needs to be done only once */ >> - if (ovsthread_once_start(&once)) { >> - rte_vhost_driver_callback_register(&virtio_net_device_ops); >> - rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4 >> - | 1ULL << VIRTIO_NET_F_HOST_TSO6 >> - | 1ULL << VIRTIO_NET_F_CSUM); >> - ovs_thread_create("vhost_thread", start_vhost_loop, NULL); >> - >> - ovsthread_once_done(&once); >> - } >> + rte_eth_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4 >> + | 1ULL << VIRTIO_NET_F_HOST_TSO6 >> + | 1ULL << VIRTIO_NET_F_CSUM); >> >> return 0; >> } >> @@ -2690,7 +2428,17 @@ netdev_dpdk_ring_send(struct netdev *netdev, int qid, >> dp_packet_rss_invalidate(batch->packets[i]); >> } >> >> - netdev_dpdk_send__(dev, qid, batch, may_steal, concurrent_txq); >> + if (OVS_UNLIKELY(concurrent_txq)) { >> + qid = qid % dev->up.n_txq; >> + rte_spinlock_lock(&dev->tx_q[qid].tx_lock); >> + } >> + >> + netdev_dpdk_send__(dev, qid, batch, may_steal); >> + >> + if (OVS_UNLIKELY(concurrent_txq)) { >> + rte_spinlock_unlock(&dev->tx_q[qid].tx_lock); >> + } >> + >> return 0; >> } >> >> @@ -2985,10 +2733,6 @@ dpdk_vhost_reconfigure_helper(struct netdev_dpdk *dev) >> netdev_change_seq_changed(&dev->up); >> } >> } >> - >> - if (netdev_dpdk_get_vid(dev) >= 0) { >> - dev->vhost_reconfigured = true; >> - } >> } >> >> static int >> @@ -3007,6 +2751,7 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev >> *netdev) >> { >> struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); >> int err = 0; >> + int sid = -1; >> >> ovs_mutex_lock(&dev->mutex); >> >> @@ -3020,14 +2765,37 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev >> *netdev) >> if (!(dev->vhost_driver_flags & RTE_VHOST_USER_CLIENT) >> && strlen(dev->vhost_id)) { >> /* Register client-mode device */ >> - err = rte_vhost_driver_register(dev->vhost_id, >> - RTE_VHOST_USER_CLIENT); >> - if (err) { >> - VLOG_ERR("vhost-user device setup failure for device %s\n", >> - dev->vhost_id); >> - } else { >> - /* Configuration successful */ >> + err = dpdk_attach_vhost_pmd(dev, 1); >> + >> + if (!err) { >> + sid = rte_eth_dev_socket_id(dev->port_id); >> + dev->socket_id = sid < 0 ? SOCKET0 : sid; >> dev->vhost_driver_flags |= RTE_VHOST_USER_CLIENT; >> + >> + rte_eth_dev_callback_register(dev->port_id, >> + RTE_ETH_EVENT_QUEUE_STATE, >> + vring_state_changed_callback, >> NULL); >> + rte_eth_dev_callback_register(dev->port_id, >> + RTE_ETH_EVENT_INTR_LSC, >> + link_status_changed_callback, >> NULL); >> + >> + rte_eth_dev_stop(dev->port_id); >> + rte_free(dev->tx_q); >> + err = dpdk_eth_dev_init(dev); >> + dev->tx_q = netdev_dpdk_alloc_txq(netdev->n_txq); >> + if (!dev->tx_q) { >> + err = ENOMEM; > > Need to go out here, because 'tx_q' will be used below. > >> + } >> + >> + /* Enable TX queue 0 by default if it wasn't disabled. */ >> + if (dev->tx_q[0].map == OVS_VHOST_QUEUE_MAP_UNKNOWN) { >> + dev->tx_q[0].map = 0; >> + } >> + >> + netdev_dpdk_remap_txqs(dev); >> + >> + netdev_change_seq_changed(netdev); >> + >> VLOG_INFO("vHost User device '%s' created in 'client' mode, " >> "using client socket '%s'", >> dev->up.name, dev->vhost_id); >> @@ -3151,14 +2919,15 @@ static const struct netdev_class dpdk_vhost_class = >> netdev_dpdk_vhost_construct, >> netdev_dpdk_vhost_destruct, >> NULL, >> - NULL, >> + netdev_dpdk_set_tx_multiq, > > Why 'netdev_dpdk_set_tx_multiq' enabled for vhost ports? > >> netdev_dpdk_vhost_send, >> - netdev_dpdk_vhost_get_carrier, >> - netdev_dpdk_vhost_get_stats, >> - NULL, >> - NULL, >> + netdev_dpdk_get_carrier, >> + netdev_dpdk_get_stats, >> + netdev_dpdk_get_features, >> + netdev_dpdk_get_status, >> netdev_dpdk_vhost_reconfigure, >> - netdev_dpdk_vhost_rxq_recv); >> + netdev_dpdk_rxq_recv); >> + >> static const struct netdev_class dpdk_vhost_client_class = >> NETDEV_DPDK_CLASS( >> "dpdkvhostuserclient", >> @@ -3166,14 +2935,14 @@ static const struct netdev_class >> dpdk_vhost_client_class = >> netdev_dpdk_vhost_client_construct, >> netdev_dpdk_vhost_destruct, >> netdev_dpdk_vhost_client_set_config, >> - NULL, >> + netdev_dpdk_set_tx_multiq, >> netdev_dpdk_vhost_send, >> - netdev_dpdk_vhost_get_carrier, >> - netdev_dpdk_vhost_get_stats, >> - NULL, >> - NULL, >> + netdev_dpdk_get_carrier, >> + netdev_dpdk_get_stats, >> + netdev_dpdk_get_features, >> + netdev_dpdk_get_status, >> netdev_dpdk_vhost_client_reconfigure, >> - netdev_dpdk_vhost_rxq_recv); >> + netdev_dpdk_vhost_client_rxq_recv); >> >> void >> netdev_dpdk_register(void) >> _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
