X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=lib%2Fnetdev-dpdk.c;h=d21bb4c43bfd75c4c4b42524ca847b617b0b0e83;hb=0bf765f753fd6cfde4918be49474fcd20659ceaa;hp=3444bb141355e61cbe0617ce9cf2fe5bf2c3b3b9;hpb=b98d7669d7c96c6d1cf8b30809faaacb1681b9e4;p=cascardo%2Fovs.git diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index 3444bb141..d21bb4c43 100644 --- a/lib/netdev-dpdk.c +++ b/lib/netdev-dpdk.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2014 Nicira, Inc. + * Copyright (c) 2014, 2015, 2016 Nicira, Inc. * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. @@ -33,6 +33,7 @@ #include "dirs.h" #include "dp-packet.h" #include "dpif-netdev.h" +#include "fatal-signal.h" #include "list.h" #include "netdev-dpdk.h" #include "netdev-provider.h" @@ -44,6 +45,7 @@ #include "ovs-rcu.h" #include "packets.h" #include "shash.h" +#include "smap.h" #include "sset.h" #include "unaligned.h" #include "timeval.h" @@ -52,6 +54,7 @@ #include "rte_config.h" #include "rte_mbuf.h" +#include "rte_meter.h" #include "rte_virtio_net.h" VLOG_DEFINE_THIS_MODULE(dpdk); @@ -65,11 +68,17 @@ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 20); /* * need to reserve tons of extra space in the mbufs so we can align the * DMA addresses to 4KB. + * The minimum mbuf size is limited to avoid scatter behaviour and drop in + * performance for standard Ethernet MTU. */ - -#define MTU_TO_MAX_LEN(mtu) ((mtu) + ETHER_HDR_LEN + ETHER_CRC_LEN) -#define MBUF_SIZE(mtu) (MTU_TO_MAX_LEN(mtu) + (512) + \ - sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) +#define ETHER_HDR_MAX_LEN (ETHER_HDR_LEN + ETHER_CRC_LEN + (2 * VLAN_HEADER_LEN)) +#define MTU_TO_FRAME_LEN(mtu) ((mtu) + ETHER_HDR_LEN + ETHER_CRC_LEN) +#define MTU_TO_MAX_FRAME_LEN(mtu) ((mtu) + ETHER_HDR_MAX_LEN) +#define FRAME_LEN_TO_MTU(frame_len) ((frame_len)- ETHER_HDR_LEN - ETHER_CRC_LEN) +#define MBUF_SIZE(mtu) ( MTU_TO_MAX_FRAME_LEN(mtu) \ + + sizeof(struct dp_packet) \ + + RTE_PKTMBUF_HEADROOM) +#define NETDEV_DPDK_MBUF_ALIGN 1024 /* Max and min number of packets in the mempool. OVS tries to allocate a * mempool with MAX_NB_MBUF: if this fails (because the system doesn't have @@ -93,6 +102,8 @@ BUILD_ASSERT_DECL((MAX_NB_MBUF / ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF)) #define NIC_PORT_RX_Q_SIZE 2048 /* Size of Physical NIC RX Queue, Max (n+32<=4096)*/ #define NIC_PORT_TX_Q_SIZE 2048 /* Size of Physical NIC TX Queue, Max (n+32<=4096)*/ +#define OVS_VHOST_MAX_QUEUE_NUM 1024 /* Maximum number of vHost TX queues. */ + static char *cuse_dev_name = NULL; /* Character device cuse_dev_name. */ static char *vhost_sock_dir = NULL; /* Location of vhost-user sockets */ @@ -136,6 +147,101 @@ static int rte_eal_init_ret = ENODEV; static struct ovs_mutex dpdk_mutex = OVS_MUTEX_INITIALIZER; +/* Quality of Service */ + +/* An instance of a QoS configuration. Always associated with a particular + * network device. + * + * Each QoS implementation subclasses this with whatever additional data it + * needs. + */ +struct qos_conf { + const struct dpdk_qos_ops *ops; +}; + +/* A particular implementation of dpdk QoS operations. + * + * The functions below return 0 if successful or a positive errno value on + * failure, except where otherwise noted. All of them must be provided, except + * where otherwise noted. + */ +struct dpdk_qos_ops { + + /* Name of the QoS type */ + const char *qos_name; + + /* Called to construct the QoS implementation on 'netdev'. The + * implementation should make the appropriate calls to configure QoS + * according to 'details'. The implementation may assume that any current + * QoS configuration already installed should be destroyed before + * constructing the new configuration. + * + * The contents of 'details' should be documented as valid for 'ovs_name' + * in the "other_config" column in the "QoS" table in vswitchd/vswitch.xml + * (which is built as ovs-vswitchd.conf.db(8)). + * + * This function must return 0 if and only if it sets 'netdev->qos_conf' + * to an initialized 'struct qos_conf'. + * + * For all QoS implementations it should always be non-null. + */ + int (*qos_construct)(struct netdev *netdev, const struct smap *details); + + /* Destroys the data structures allocated by the implementation as part of + * 'qos_conf. + * + * For all QoS implementations it should always be non-null. + */ + void (*qos_destruct)(struct netdev *netdev, struct qos_conf *conf); + + /* Retrieves details of 'netdev->qos_conf' configuration into 'details'. + * + * The contents of 'details' should be documented as valid for 'ovs_name' + * in the "other_config" column in the "QoS" table in vswitchd/vswitch.xml + * (which is built as ovs-vswitchd.conf.db(8)). + */ + int (*qos_get)(const struct netdev *netdev, struct smap *details); + + /* Reconfigures 'netdev->qos_conf' according to 'details', performing any + * required calls to complete the reconfiguration. + * + * The contents of 'details' should be documented as valid for 'ovs_name' + * in the "other_config" column in the "QoS" table in vswitchd/vswitch.xml + * (which is built as ovs-vswitchd.conf.db(8)). + * + * This function may be null if 'qos_conf' is not configurable. + */ + int (*qos_set)(struct netdev *netdev, const struct smap *details); + + /* Modify an array of rte_mbufs. The modification is specific to + * each qos implementation. + * + * The function should take and array of mbufs and an int representing + * the current number of mbufs present in the array. + * + * After the function has performed a qos modification to the array of + * mbufs it returns an int representing the number of mbufs now present in + * the array. This value is can then be passed to the port send function + * along with the modified array for transmission. + * + * For all QoS implementations it should always be non-null. + */ + int (*qos_run)(struct netdev *netdev, struct rte_mbuf **pkts, + int pkt_cnt); +}; + +/* dpdk_qos_ops for each type of user space QoS implementation */ +static const struct dpdk_qos_ops egress_policer_ops; + +/* + * Array of dpdk_qos_ops, contains pointer to all supported QoS + * operations. + */ +static const struct dpdk_qos_ops *const qos_confs[] = { + &egress_policer_ops, + NULL +}; + /* Contains all 'struct dpdk_dev's. */ static struct ovs_list dpdk_list OVS_GUARDED_BY(dpdk_mutex) = OVS_LIST_INITIALIZER(&dpdk_list); @@ -166,6 +272,8 @@ struct dpdk_tx_queue { * from concurrent access. It is used only * if the queue is shared among different * pmd threads (see 'txq_needs_locking'). */ + int map; /* Mapping of configured vhost-user queues + * to enabled by guest. */ uint64_t tsc; struct rte_mbuf *burst_pkts[MAX_TX_QUEUE_LEN]; }; @@ -181,7 +289,7 @@ struct dpdk_ring { /* For the client rings */ struct rte_ring *cring_tx; struct rte_ring *cring_rx; - int user_port_id; /* User given port no, parsed from port name */ + unsigned int user_port_id; /* User given port no, parsed from port name */ int eth_port_id; /* ethernet device port id */ struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex); }; @@ -204,7 +312,7 @@ struct netdev_dpdk { /* Protects stats */ rte_spinlock_t stats_lock; - uint8_t hwaddr[ETH_ADDR_LEN]; + struct eth_addr hwaddr; enum netdev_flags flags; struct rte_eth_link link; @@ -215,12 +323,9 @@ struct netdev_dpdk { * If the numbers match, 'txq_needs_locking' is false, otherwise it is * true and we will take a spinlock on transmission */ int real_n_txq; + int real_n_rxq; bool txq_needs_locking; - /* Spinlock for vhost transmission. Other DPDK devices use spinlocks in - * dpdk_tx_queue */ - rte_spinlock_t vhost_tx_lock; - /* virtio-net structure for vhost device */ OVSRCU_TYPE(struct virtio_net *) virtio_dev; @@ -229,6 +334,11 @@ struct netdev_dpdk { /* In dpdk_list. */ struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex); + + /* QoS configuration and lock for the device */ + struct qos_conf *qos_conf; + rte_spinlock_t qos_lock; + }; struct netdev_rxq_dpdk { @@ -236,7 +346,7 @@ struct netdev_rxq_dpdk { int port_id; }; -static bool thread_is_pmd(void); +static bool dpdk_thread_is_pmd(void); static int netdev_dpdk_construct(struct netdev *); @@ -248,6 +358,22 @@ is_dpdk_class(const struct netdev_class *class) return class->construct == netdev_dpdk_construct; } +/* DPDK NIC drivers allocate RX buffers at a particular granularity, typically + * aligned at 1k or less. If a declared mbuf size is not a multiple of this + * value, insufficient buffers are allocated to accomodate the packet in its + * entirety. Furthermore, certain drivers need to ensure that there is also + * sufficient space in the Rx buffer to accommodate two VLAN tags (for QinQ + * frames). If the RX buffer is too small, then the driver enables scatter RX + * behaviour, which reduces performance. To prevent this, use a buffer size that + * is closest to 'mtu', but which satisfies the aforementioned criteria. + */ +static uint32_t +dpdk_buf_size(int mtu) +{ + return ROUND_UP((MTU_TO_MAX_FRAME_LEN(mtu) + RTE_PKTMBUF_HEADROOM), + NETDEV_DPDK_MBUF_ALIGN); +} + /* XXX: use dpdk malloc for entire OVS. in fact huge page should be used * for all other segments data, bss and text. */ @@ -273,34 +399,6 @@ free_dpdk_buf(struct dp_packet *p) rte_pktmbuf_free_seg(pkt); } -static void -__rte_pktmbuf_init(struct rte_mempool *mp, - void *opaque_arg OVS_UNUSED, - void *_m, - unsigned i OVS_UNUSED) -{ - struct rte_mbuf *m = _m; - uint32_t buf_len = mp->elt_size - sizeof(struct dp_packet); - - RTE_MBUF_ASSERT(mp->elt_size >= sizeof(struct dp_packet)); - - memset(m, 0, mp->elt_size); - - /* start of buffer is just after mbuf structure */ - m->buf_addr = (char *)m + sizeof(struct dp_packet); - m->buf_physaddr = rte_mempool_virt2phy(mp, m) + - sizeof(struct dp_packet); - m->buf_len = (uint16_t)buf_len; - - /* keep some headroom between start of buffer and data */ - m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, m->buf_len); - - /* init some constant fields */ - m->pool = mp; - m->nb_segs = 1; - m->port = 0xff; -} - static void ovs_rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg OVS_UNUSED, @@ -309,7 +407,7 @@ ovs_rte_pktmbuf_init(struct rte_mempool *mp, { struct rte_mbuf *m = _m; - __rte_pktmbuf_init(mp, opaque_arg, _m, i); + rte_pktmbuf_init(mp, opaque_arg, _m, i); dp_packet_init_dpdk((struct dp_packet *) m, m->buf_len); } @@ -320,6 +418,7 @@ dpdk_mp_get(int socket_id, int mtu) OVS_REQUIRES(dpdk_mutex) struct dpdk_mp *dmp = NULL; char mp_name[RTE_MEMPOOL_NAMESIZE]; unsigned mp_size; + struct rte_pktmbuf_pool_private mbp_priv; LIST_FOR_EACH (dmp, list_node, &dpdk_mp_list) { if (dmp->socket_id == socket_id && dmp->mtu == mtu) { @@ -332,6 +431,8 @@ dpdk_mp_get(int socket_id, int mtu) OVS_REQUIRES(dpdk_mutex) dmp->socket_id = socket_id; dmp->mtu = mtu; dmp->refcount = 1; + mbp_priv.mbuf_data_room_size = MBUF_SIZE(mtu) - sizeof(struct dp_packet); + mbp_priv.mbuf_priv_size = sizeof (struct dp_packet) - sizeof (struct rte_mbuf); mp_size = MAX_NB_MBUF; do { @@ -343,7 +444,7 @@ dpdk_mp_get(int socket_id, int mtu) OVS_REQUIRES(dpdk_mutex) dmp->mp = rte_mempool_create(mp_name, mp_size, MBUF_SIZE(mtu), MP_CACHE_SZ, sizeof(struct rte_pktmbuf_pool_private), - rte_pktmbuf_pool_init, NULL, + rte_pktmbuf_pool_init, &mbp_priv, ovs_rte_pktmbuf_init, NULL, socket_id, 0); } while (!dmp->mp && rte_errno == ENOMEM && (mp_size /= 2) >= MIN_NB_MBUF); @@ -524,9 +625,9 @@ dpdk_eth_dev_init(struct netdev_dpdk *dev) OVS_REQUIRES(dpdk_mutex) memset(ð_addr, 0x0, sizeof(eth_addr)); rte_eth_macaddr_get(dev->port_id, ð_addr); VLOG_INFO_RL(&rl, "Port %d: "ETH_ADDR_FMT"", - dev->port_id, ETH_ADDR_ARGS(eth_addr.addr_bytes)); + dev->port_id, ETH_ADDR_BYTES_ARGS(eth_addr.addr_bytes)); - memcpy(dev->hwaddr, eth_addr.addr_bytes, ETH_ADDR_LEN); + memcpy(dev->hwaddr.ea, eth_addr.addr_bytes, ETH_ADDR_LEN); rte_eth_link_get_nowait(dev->port_id, &dev->link); mbp_priv = rte_mempool_get_priv(dev->dpdk_mp->mp); @@ -568,6 +669,9 @@ netdev_dpdk_alloc_txq(struct netdev_dpdk *netdev, unsigned int n_txqs) /* Queues are shared among CPUs. Always flush */ netdev->tx_q[i].flush_tx = true; } + + /* Initialize map for vhost devices. */ + netdev->tx_q[i].map = -1; rte_spinlock_init(&netdev->tx_q[i].tx_lock); } } @@ -580,6 +684,7 @@ netdev_dpdk_init(struct netdev *netdev_, unsigned int port_no, struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); int sid; int err = 0; + uint32_t buf_size; ovs_mutex_init(&netdev->mutex); ovs_mutex_lock(&netdev->mutex); @@ -600,16 +705,22 @@ netdev_dpdk_init(struct netdev *netdev_, unsigned int port_no, netdev->type = type; netdev->flags = 0; netdev->mtu = ETHER_MTU; - netdev->max_packet_len = MTU_TO_MAX_LEN(netdev->mtu); + netdev->max_packet_len = MTU_TO_FRAME_LEN(netdev->mtu); - netdev->dpdk_mp = dpdk_mp_get(netdev->socket_id, netdev->mtu); + buf_size = dpdk_buf_size(netdev->mtu); + netdev->dpdk_mp = dpdk_mp_get(netdev->socket_id, FRAME_LEN_TO_MTU(buf_size)); if (!netdev->dpdk_mp) { err = ENOMEM; goto unlock; } + /* Initialise QoS configuration to NULL and qos lock to unlocked */ + netdev->qos_conf = NULL; + rte_spinlock_init(&netdev->qos_lock); + netdev_->n_txq = NR_QUEUE; netdev_->n_rxq = NR_QUEUE; + netdev_->requested_n_rxq = NR_QUEUE; netdev->real_n_txq = NR_QUEUE; if (type == DPDK_DEV_ETH) { @@ -618,6 +729,8 @@ netdev_dpdk_init(struct netdev *netdev_, unsigned int port_no, if (err) { goto unlock; } + } else { + netdev_dpdk_alloc_txq(netdev, OVS_VHOST_MAX_QUEUE_NUM); } list_push_back(&dpdk_list, &netdev->list_node); @@ -630,6 +743,8 @@ unlock: return err; } +/* dev_name must be the prefix followed by a positive decimal number. + * (no leading + or - signs are allowed) */ static int dpdk_dev_parse_name(const char dev_name[], const char prefix[], unsigned int *port_no) @@ -641,20 +756,21 @@ dpdk_dev_parse_name(const char dev_name[], const char prefix[], } cport = dev_name + strlen(prefix); - *port_no = strtol(cport, NULL, 0); /* string must be null terminated */ - return 0; + + if (str_to_uint(cport, 10, port_no)) { + return 0; + } else { + return ENODEV; + } } static int vhost_construct_helper(struct netdev *netdev_) OVS_REQUIRES(dpdk_mutex) { - struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); - if (rte_eal_init_ret) { return rte_eal_init_ret; } - rte_spinlock_init(&netdev->vhost_tx_lock); return netdev_dpdk_init(netdev_, -1, DPDK_DEV_VHOST); } @@ -675,21 +791,37 @@ static int netdev_dpdk_vhost_user_construct(struct netdev *netdev_) { struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + const char *name = netdev_->name; int err; + /* '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, '\\')) { + VLOG_ERR("\"%s\" is not a valid name for a vhost-user port. " + "A valid name must not include '/' or '\\'", + name); + return EINVAL; + } + ovs_mutex_lock(&dpdk_mutex); /* Take the name of the vhost-user port and append it to the location where * the socket is to be created, then register the socket. */ snprintf(netdev->vhost_id, sizeof(netdev->vhost_id), "%s/%s", - vhost_sock_dir, netdev_->name); + vhost_sock_dir, name); + err = rte_vhost_driver_register(netdev->vhost_id); if (err) { VLOG_ERR("vhost-user socket device setup failure for socket %s\n", netdev->vhost_id); + } else { + fatal_signal_add_file_to_unlink(netdev->vhost_id); + VLOG_INFO("Socket %s created for vhost-user port %s\n", + netdev->vhost_id, name); + err = vhost_construct_helper(netdev_); } - VLOG_INFO("Socket %s created for vhost-user port %s\n", netdev->vhost_id, netdev_->name); - err = vhost_construct_helper(netdev_); + ovs_mutex_unlock(&dpdk_mutex); return err; } @@ -743,6 +875,12 @@ netdev_dpdk_vhost_destruct(struct netdev *netdev_) return; } + if (rte_vhost_driver_unregister(dev->vhost_id)) { + VLOG_ERR("Unable to remove vhost-user socket %s", dev->vhost_id); + } else { + fatal_signal_remove_file_to_unlink(dev->vhost_id); + } + ovs_mutex_lock(&dpdk_mutex); list_remove(&dev->list_node); dpdk_mp_put(dev->dpdk_mp); @@ -758,20 +896,35 @@ netdev_dpdk_dealloc(struct netdev *netdev_) } static int -netdev_dpdk_get_config(const struct netdev *netdev_, struct smap *args) +netdev_dpdk_get_config(const struct netdev *netdev, struct smap *args) { - struct netdev_dpdk *dev = netdev_dpdk_cast(netdev_); + struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); ovs_mutex_lock(&dev->mutex); - smap_add_format(args, "configured_rx_queues", "%d", netdev_->n_rxq); - smap_add_format(args, "requested_tx_queues", "%d", netdev_->n_txq); + smap_add_format(args, "requested_rx_queues", "%d", netdev->requested_n_rxq); + smap_add_format(args, "configured_rx_queues", "%d", netdev->n_rxq); + smap_add_format(args, "requested_tx_queues", "%d", netdev->n_txq); smap_add_format(args, "configured_tx_queues", "%d", dev->real_n_txq); ovs_mutex_unlock(&dev->mutex); return 0; } +static int +netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args) +{ + struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); + + ovs_mutex_lock(&dev->mutex); + netdev->requested_n_rxq = MAX(smap_get_int(args, "n_rxq", + netdev->requested_n_rxq), 1); + netdev_change_seq_changed(netdev); + ovs_mutex_unlock(&dev->mutex); + + return 0; +} + static int netdev_dpdk_get_numa_id(const struct netdev *netdev_) { @@ -824,7 +977,7 @@ netdev_dpdk_set_multiq(struct netdev *netdev_, unsigned int n_txq, } static int -netdev_dpdk_vhost_set_multiq(struct netdev *netdev_, unsigned int n_txq, +netdev_dpdk_vhost_cuse_set_multiq(struct netdev *netdev_, unsigned int n_txq, unsigned int n_rxq) { struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); @@ -840,6 +993,30 @@ netdev_dpdk_vhost_set_multiq(struct netdev *netdev_, unsigned int n_txq, netdev->up.n_txq = n_txq; netdev->real_n_txq = 1; netdev->up.n_rxq = 1; + netdev->txq_needs_locking = netdev->real_n_txq != netdev->up.n_txq; + + ovs_mutex_unlock(&netdev->mutex); + ovs_mutex_unlock(&dpdk_mutex); + + return err; +} + +static int +netdev_dpdk_vhost_set_multiq(struct netdev *netdev_, unsigned int n_txq, + unsigned int n_rxq) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + int err = 0; + + if (netdev->up.n_txq == n_txq && netdev->up.n_rxq == n_rxq) { + return err; + } + + ovs_mutex_lock(&dpdk_mutex); + ovs_mutex_lock(&netdev->mutex); + + netdev->up.n_txq = n_txq; + netdev->up.n_rxq = n_rxq; ovs_mutex_unlock(&netdev->mutex); ovs_mutex_unlock(&dpdk_mutex); @@ -939,6 +1116,35 @@ is_vhost_running(struct virtio_net *dev) return (dev != NULL && (dev->flags & VIRTIO_DEV_RUNNING)); } +static inline void +netdev_dpdk_vhost_update_rx_counters(struct netdev_stats *stats, + struct dp_packet **packets, int count) +{ + int i; + struct dp_packet *packet; + + stats->rx_packets += count; + for (i = 0; i < count; i++) { + packet = packets[i]; + + if (OVS_UNLIKELY(dp_packet_size(packet) < 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; + } + + 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 += dp_packet_size(packet); + } +} + /* * The receive path for the vhost port is the TX path out from guest. */ @@ -950,14 +1156,18 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq_, struct netdev *netdev = rx->up.netdev; struct netdev_dpdk *vhost_dev = netdev_dpdk_cast(netdev); struct virtio_net *virtio_dev = netdev_dpdk_get_virtio(vhost_dev); - int qid = 1; + int qid = rxq_->queue_id; uint16_t nb_rx = 0; if (OVS_UNLIKELY(!is_vhost_running(virtio_dev))) { return EAGAIN; } - nb_rx = rte_vhost_dequeue_burst(virtio_dev, qid, + if (rxq_->queue_id >= vhost_dev->real_n_rxq) { + return EOPNOTSUPP; + } + + nb_rx = rte_vhost_dequeue_burst(virtio_dev, qid * VIRTIO_QNUM + VIRTIO_TXQ, vhost_dev->dpdk_mp->mp, (struct rte_mbuf **)packets, NETDEV_MAX_BURST); @@ -966,7 +1176,7 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq_, } rte_spinlock_lock(&vhost_dev->stats_lock); - vhost_dev->stats.rx_packets += (uint64_t)nb_rx; + netdev_dpdk_vhost_update_rx_counters(&vhost_dev->stats, packets, nb_rx); rte_spinlock_unlock(&vhost_dev->stats_lock); *c = (int) nb_rx; @@ -1003,30 +1213,72 @@ netdev_dpdk_rxq_recv(struct netdev_rxq *rxq_, struct dp_packet **packets, return 0; } +static inline int +netdev_dpdk_qos_run__(struct netdev_dpdk *dev, struct rte_mbuf **pkts, + int cnt) +{ + struct netdev *netdev = &dev->up; + + if (dev->qos_conf != NULL) { + rte_spinlock_lock(&dev->qos_lock); + if (dev->qos_conf != NULL) { + cnt = dev->qos_conf->ops->qos_run(netdev, pkts, cnt); + } + rte_spinlock_unlock(&dev->qos_lock); + } + + 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, struct dp_packet **pkts, - int cnt, bool may_steal) +__netdev_dpdk_vhost_send(struct netdev *netdev, int qid, + struct dp_packet **pkts, int cnt, + bool may_steal) { struct netdev_dpdk *vhost_dev = netdev_dpdk_cast(netdev); struct virtio_net *virtio_dev = netdev_dpdk_get_virtio(vhost_dev); struct rte_mbuf **cur_pkts = (struct rte_mbuf **) pkts; unsigned int total_pkts = cnt; + unsigned int qos_pkts = cnt; uint64_t start = 0; - if (OVS_UNLIKELY(!is_vhost_running(virtio_dev))) { + qid = vhost_dev->tx_q[qid % vhost_dev->real_n_txq].map; + + if (OVS_UNLIKELY(!is_vhost_running(virtio_dev) || qid == -1)) { rte_spinlock_lock(&vhost_dev->stats_lock); vhost_dev->stats.tx_dropped+= cnt; rte_spinlock_unlock(&vhost_dev->stats_lock); goto out; } - /* There is vHost TX single queue, So we need to lock it for TX. */ - rte_spinlock_lock(&vhost_dev->vhost_tx_lock); + rte_spinlock_lock(&vhost_dev->tx_q[qid].tx_lock); + + /* Check has QoS has been configured for the netdev */ + cnt = netdev_dpdk_qos_run__(vhost_dev, cur_pkts, cnt); + qos_pkts -= cnt; do { + int vhost_qid = qid * VIRTIO_QNUM + VIRTIO_RXQ; unsigned int tx_pkts; - tx_pkts = rte_vhost_enqueue_burst(virtio_dev, VIRTIO_RXQ, + tx_pkts = rte_vhost_enqueue_burst(virtio_dev, vhost_qid, cur_pkts, cnt); if (OVS_LIKELY(tx_pkts)) { /* Packets have been sent.*/ @@ -1045,7 +1297,7 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, struct dp_packet **pkts, * Unable to enqueue packets to vhost interface. * Check available entries before retrying. */ - while (!rte_vring_available_entries(virtio_dev, VIRTIO_RXQ)) { + while (!rte_vring_available_entries(virtio_dev, vhost_qid)) { if (OVS_UNLIKELY((rte_get_timer_cycles() - start) > timeout)) { expired = 1; break; @@ -1057,11 +1309,13 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, struct dp_packet **pkts, } } } while (cnt); - rte_spinlock_unlock(&vhost_dev->vhost_tx_lock); + + rte_spinlock_unlock(&vhost_dev->tx_q[qid].tx_lock); rte_spinlock_lock(&vhost_dev->stats_lock); - vhost_dev->stats.tx_packets += (total_pkts - cnt); - vhost_dev->stats.tx_dropped += cnt; + cnt += qos_pkts; + netdev_dpdk_vhost_update_tx_counters(&vhost_dev->stats, pkts, total_pkts, + cnt); rte_spinlock_unlock(&vhost_dev->stats_lock); out: @@ -1124,7 +1378,7 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet **pkts, /* If we are on a non pmd thread we have to use the mempool mutex, because * every non pmd thread shares the same mempool cache */ - if (!thread_is_pmd()) { + if (!dpdk_thread_is_pmd()) { ovs_mutex_lock(&nonpmd_mempool_mutex); } @@ -1155,26 +1409,32 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet **pkts, newcnt++; } - if (OVS_UNLIKELY(dropped)) { - rte_spinlock_lock(&dev->stats_lock); - dev->stats.tx_dropped += dropped; - rte_spinlock_unlock(&dev->stats_lock); - } - if (dev->type == DPDK_DEV_VHOST) { - __netdev_dpdk_vhost_send(netdev, (struct dp_packet **) mbufs, newcnt, true); + __netdev_dpdk_vhost_send(netdev, qid, (struct dp_packet **) mbufs, newcnt, true); } else { + unsigned int qos_pkts = newcnt; + + /* Check if QoS has been configured for this netdev. */ + newcnt = netdev_dpdk_qos_run__(dev, mbufs, newcnt); + + dropped += qos_pkts - newcnt; dpdk_queue_pkts(dev, qid, mbufs, newcnt); dpdk_queue_flush(dev, qid); } - if (!thread_is_pmd()) { + if (OVS_UNLIKELY(dropped)) { + rte_spinlock_lock(&dev->stats_lock); + dev->stats.tx_dropped += dropped; + rte_spinlock_unlock(&dev->stats_lock); + } + + if (!dpdk_thread_is_pmd()) { ovs_mutex_unlock(&nonpmd_mempool_mutex); } } static int -netdev_dpdk_vhost_send(struct netdev *netdev, int qid OVS_UNUSED, struct dp_packet **pkts, +netdev_dpdk_vhost_send(struct netdev *netdev, int qid, struct dp_packet **pkts, int cnt, bool may_steal) { if (OVS_UNLIKELY(pkts[0]->source != DPBUF_DPDK)) { @@ -1187,7 +1447,7 @@ netdev_dpdk_vhost_send(struct netdev *netdev, int qid OVS_UNUSED, struct dp_pack } } } else { - __netdev_dpdk_vhost_send(netdev, pkts, cnt, may_steal); + __netdev_dpdk_vhost_send(netdev, qid, pkts, cnt, may_steal); } return 0; } @@ -1217,15 +1477,24 @@ netdev_dpdk_send__(struct netdev_dpdk *dev, int qid, } else { int next_tx_idx = 0; int dropped = 0; + unsigned int qos_pkts = 0; + unsigned int temp_cnt = 0; for (i = 0; i < cnt; i++) { int size = dp_packet_size(pkts[i]); if (OVS_UNLIKELY(size > dev->max_packet_len)) { if (next_tx_idx != i) { + temp_cnt = i - next_tx_idx; + qos_pkts = temp_cnt; + + temp_cnt = netdev_dpdk_qos_run__(dev, (struct rte_mbuf**)pkts, + temp_cnt); + dropped += qos_pkts - temp_cnt; dpdk_queue_pkts(dev, qid, (struct rte_mbuf **)&pkts[next_tx_idx], - i-next_tx_idx); + temp_cnt); + } VLOG_WARN_RL(&rl, "Too big size %d max_packet_len %d", @@ -1237,9 +1506,13 @@ netdev_dpdk_send__(struct netdev_dpdk *dev, int qid, } } if (next_tx_idx != cnt) { - dpdk_queue_pkts(dev, qid, - (struct rte_mbuf **)&pkts[next_tx_idx], - cnt-next_tx_idx); + cnt -= next_tx_idx; + qos_pkts = cnt; + + cnt = netdev_dpdk_qos_run__(dev, (struct rte_mbuf**)pkts, cnt); + dropped += qos_pkts - cnt; + dpdk_queue_pkts(dev, qid, (struct rte_mbuf **)&pkts[next_tx_idx], + cnt); } if (OVS_UNLIKELY(dropped)) { @@ -1265,14 +1538,13 @@ netdev_dpdk_eth_send(struct netdev *netdev, int qid, } static int -netdev_dpdk_set_etheraddr(struct netdev *netdev, - const uint8_t mac[ETH_ADDR_LEN]) +netdev_dpdk_set_etheraddr(struct netdev *netdev, const struct eth_addr mac) { struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); ovs_mutex_lock(&dev->mutex); if (!eth_addr_equals(dev->hwaddr, mac)) { - memcpy(dev->hwaddr, mac, ETH_ADDR_LEN); + dev->hwaddr = mac; netdev_change_seq_changed(netdev); } ovs_mutex_unlock(&dev->mutex); @@ -1281,13 +1553,12 @@ netdev_dpdk_set_etheraddr(struct netdev *netdev, } static int -netdev_dpdk_get_etheraddr(const struct netdev *netdev, - uint8_t mac[ETH_ADDR_LEN]) +netdev_dpdk_get_etheraddr(const struct netdev *netdev, struct eth_addr *mac) { struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); ovs_mutex_lock(&dev->mutex); - memcpy(mac, dev->hwaddr, ETH_ADDR_LEN); + *mac = dev->hwaddr; ovs_mutex_unlock(&dev->mutex); return 0; @@ -1309,9 +1580,10 @@ static int netdev_dpdk_set_mtu(const struct netdev *netdev, int mtu) { struct netdev_dpdk *dev = netdev_dpdk_cast(netdev); - int old_mtu, err; + int old_mtu, err, dpdk_mtu; struct dpdk_mp *old_mp; struct dpdk_mp *mp; + uint32_t buf_size; ovs_mutex_lock(&dpdk_mutex); ovs_mutex_lock(&dev->mutex); @@ -1320,7 +1592,10 @@ netdev_dpdk_set_mtu(const struct netdev *netdev, int mtu) goto out; } - mp = dpdk_mp_get(dev->socket_id, dev->mtu); + buf_size = dpdk_buf_size(mtu); + dpdk_mtu = FRAME_LEN_TO_MTU(buf_size); + + mp = dpdk_mp_get(dev->socket_id, dpdk_mtu); if (!mp) { err = ENOMEM; goto out; @@ -1332,14 +1607,14 @@ netdev_dpdk_set_mtu(const struct netdev *netdev, int mtu) old_mp = dev->dpdk_mp; dev->dpdk_mp = mp; dev->mtu = mtu; - dev->max_packet_len = MTU_TO_MAX_LEN(dev->mtu); + dev->max_packet_len = MTU_TO_FRAME_LEN(dev->mtu); err = dpdk_eth_dev_init(dev); if (err) { dpdk_mp_put(mp); dev->mtu = old_mtu; dev->dpdk_mp = old_mp; - dev->max_packet_len = MTU_TO_MAX_LEN(dev->mtu); + dev->max_packet_len = MTU_TO_FRAME_LEN(dev->mtu); dpdk_eth_dev_init(dev); goto out; } @@ -1364,14 +1639,10 @@ netdev_dpdk_vhost_get_stats(const struct netdev *netdev, ovs_mutex_lock(&dev->mutex); memset(stats, 0, sizeof(*stats)); /* Unsupported Stats */ - stats->rx_errors = UINT64_MAX; - stats->tx_errors = UINT64_MAX; - stats->multicast = UINT64_MAX; stats->collisions = UINT64_MAX; stats->rx_crc_errors = UINT64_MAX; stats->rx_fifo_errors = UINT64_MAX; stats->rx_frame_errors = UINT64_MAX; - stats->rx_length_errors = UINT64_MAX; stats->rx_missed_errors = UINT64_MAX; stats->rx_over_errors = UINT64_MAX; stats->tx_aborted_errors = UINT64_MAX; @@ -1380,16 +1651,20 @@ netdev_dpdk_vhost_get_stats(const struct netdev *netdev, stats->tx_fifo_errors = UINT64_MAX; stats->tx_heartbeat_errors = UINT64_MAX; stats->tx_window_errors = UINT64_MAX; - stats->rx_bytes += UINT64_MAX; stats->rx_dropped += UINT64_MAX; - stats->tx_bytes += UINT64_MAX; rte_spinlock_lock(&dev->stats_lock); /* Supported Stats */ stats->rx_packets += dev->stats.rx_packets; stats->tx_packets += dev->stats.tx_packets; 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; rte_spinlock_unlock(&dev->stats_lock); + ovs_mutex_unlock(&dev->mutex); return 0; @@ -1412,13 +1687,33 @@ netdev_dpdk_get_stats(const struct netdev *netdev, struct netdev_stats *stats) stats->tx_packets = rte_stats.opackets; stats->rx_bytes = rte_stats.ibytes; stats->tx_bytes = rte_stats.obytes; - stats->rx_errors = rte_stats.ierrors; + /* 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; stats->multicast = rte_stats.imcasts; rte_spinlock_lock(&dev->stats_lock); stats->tx_dropped = dev->stats.tx_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->collisions = UINT64_MAX; + + stats->rx_length_errors = UINT64_MAX; + stats->rx_over_errors = UINT64_MAX; + stats->rx_crc_errors = UINT64_MAX; + stats->rx_frame_errors = UINT64_MAX; + stats->rx_fifo_errors = UINT64_MAX; + stats->rx_missed_errors = rte_stats.imissed; + + stats->tx_aborted_errors = UINT64_MAX; + stats->tx_carrier_errors = UINT64_MAX; + stats->tx_fifo_errors = UINT64_MAX; + stats->tx_heartbeat_errors = UINT64_MAX; + stats->tx_window_errors = UINT64_MAX; + ovs_mutex_unlock(&dev->mutex); return 0; @@ -1608,7 +1903,7 @@ netdev_dpdk_get_status(const struct netdev *netdev_, struct smap *args) smap_add_format(args, "numa_id", "%d", rte_eth_dev_socket_id(dev->port_id)); smap_add_format(args, "driver_name", "%s", dev_info.driver_name); smap_add_format(args, "min_rx_bufsize", "%u", dev_info.min_rx_bufsize); - smap_add_format(args, "max_rx_pktlen", "%u", dev_info.max_rx_pktlen); + smap_add_format(args, "max_rx_pktlen", "%u", dev->max_packet_len); smap_add_format(args, "max_rx_queues", "%u", dev_info.max_rx_queues); smap_add_format(args, "max_tx_queues", "%u", dev_info.max_tx_queues); smap_add_format(args, "max_mac_addrs", "%u", dev_info.max_mac_addrs); @@ -1616,8 +1911,12 @@ 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); - 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_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; } @@ -1685,8 +1984,78 @@ netdev_dpdk_set_admin_state(struct unixctl_conn *conn, int argc, static void set_irq_status(struct virtio_net *dev) { - dev->virtqueue[VIRTIO_RXQ]->used->flags = VRING_USED_F_NO_NOTIFY; - dev->virtqueue[VIRTIO_TXQ]->used->flags = VRING_USED_F_NO_NOTIFY; + uint32_t i; + uint64_t idx; + + for (i = 0; i < dev->virt_qp_nb; i++) { + idx = i * VIRTIO_QNUM; + rte_vhost_enable_guest_notification(dev, idx + VIRTIO_RXQ, 0); + rte_vhost_enable_guest_notification(dev, idx + VIRTIO_TXQ, 0); + } +} + +/* + * Fixes mapping for vhost-user tx queues. Must be called after each + * enabling/disabling of queues and real_n_txq modifications. + */ +static void +netdev_dpdk_remap_txqs(struct netdev_dpdk *netdev) + OVS_REQUIRES(netdev->mutex) +{ + int *enabled_queues, n_enabled = 0; + int i, k, total_txqs = netdev->real_n_txq; + + enabled_queues = dpdk_rte_mzalloc(total_txqs * sizeof *enabled_queues); + + for (i = 0; i < total_txqs; i++) { + /* Enabled queues always mapped to themselves. */ + if (netdev->tx_q[i].map == i) { + enabled_queues[n_enabled++] = i; + } + } + + if (n_enabled == 0 && total_txqs != 0) { + enabled_queues[0] = -1; + n_enabled = 1; + } + + k = 0; + for (i = 0; i < total_txqs; i++) { + if (netdev->tx_q[i].map != i) { + netdev->tx_q[i].map = enabled_queues[k]; + k = (k + 1) % n_enabled; + } + } + + VLOG_DBG("TX queue mapping for %s\n", netdev->vhost_id); + for (i = 0; i < total_txqs; i++) { + VLOG_DBG("%2d --> %2d", i, netdev->tx_q[i].map); + } + + rte_free(enabled_queues); +} + +static int +netdev_dpdk_vhost_set_queues(struct netdev_dpdk *netdev, struct virtio_net *dev) + OVS_REQUIRES(netdev->mutex) +{ + uint32_t qp_num; + + qp_num = dev->virt_qp_nb; + if (qp_num > netdev->up.n_rxq) { + VLOG_ERR("vHost Device '%s' %"PRIu64" can't be added - " + "too many queues %d > %d", dev->ifname, dev->device_fh, + qp_num, netdev->up.n_rxq); + return -1; + } + + netdev->real_n_rxq = qp_num; + netdev->real_n_txq = qp_num; + netdev->txq_needs_locking = true; + + netdev_dpdk_remap_txqs(netdev); + + return 0; } /* @@ -1703,26 +2072,31 @@ new_device(struct virtio_net *dev) LIST_FOR_EACH(netdev, list_node, &dpdk_list) { if (strncmp(dev->ifname, netdev->vhost_id, IF_NAME_SZ) == 0) { ovs_mutex_lock(&netdev->mutex); + if (netdev_dpdk_vhost_set_queues(netdev, dev)) { + ovs_mutex_unlock(&netdev->mutex); + ovs_mutex_unlock(&dpdk_mutex); + return -1; + } ovsrcu_set(&netdev->virtio_dev, dev); - ovs_mutex_unlock(&netdev->mutex); exists = true; dev->flags |= VIRTIO_DEV_RUNNING; /* Disable notifications. */ set_irq_status(dev); + ovs_mutex_unlock(&netdev->mutex); break; } } ovs_mutex_unlock(&dpdk_mutex); if (!exists) { - VLOG_INFO("vHost Device '%s' (%ld) can't be added - name not found", - dev->ifname, dev->device_fh); + VLOG_INFO("vHost Device '%s' %"PRIu64" can't be added - name not " + "found", dev->ifname, dev->device_fh); return -1; } - VLOG_INFO("vHost Device '%s' (%ld) has been added", - dev->ifname, dev->device_fh); + VLOG_INFO("vHost Device '%s' %"PRIu64" has been added", dev->ifname, + dev->device_fh); return 0; } @@ -1736,6 +2110,7 @@ static void destroy_device(volatile struct virtio_net *dev) { struct netdev_dpdk *vhost_dev; + bool exists = false; ovs_mutex_lock(&dpdk_mutex); LIST_FOR_EACH (vhost_dev, list_node, &dpdk_list) { @@ -1744,24 +2119,73 @@ destroy_device(volatile struct virtio_net *dev) ovs_mutex_lock(&vhost_dev->mutex); dev->flags &= ~VIRTIO_DEV_RUNNING; ovsrcu_set(&vhost_dev->virtio_dev, NULL); + exists = true; ovs_mutex_unlock(&vhost_dev->mutex); + break; + } + } - /* - * Wait for other threads to quiesce before - * setting the virtio_dev to NULL. - */ - ovsrcu_synchronize(); - /* - * As call to ovsrcu_synchronize() will end the quiescent state, - * put thread back into quiescent state before returning. - */ - ovsrcu_quiesce_start(); + ovs_mutex_unlock(&dpdk_mutex); + + if (exists == true) { + /* + * 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' %"PRIu64" has been removed", dev->ifname, + dev->device_fh); + } else { + VLOG_INFO("vHost Device '%s' %"PRIu64" not found", dev->ifname, + dev->device_fh); + } + +} + +static int +vring_state_changed(struct virtio_net *dev, uint16_t queue_id, int enable) +{ + struct netdev_dpdk *vhost_dev; + bool exists = false; + int qid = queue_id / VIRTIO_QNUM; + + if (queue_id % VIRTIO_QNUM == VIRTIO_TXQ) { + return 0; + } + + ovs_mutex_lock(&dpdk_mutex); + LIST_FOR_EACH (vhost_dev, list_node, &dpdk_list) { + if (strncmp(dev->ifname, vhost_dev->vhost_id, IF_NAME_SZ) == 0) { + ovs_mutex_lock(&vhost_dev->mutex); + if (enable) { + vhost_dev->tx_q[qid].map = qid; + } else { + vhost_dev->tx_q[qid].map = -1; + } + netdev_dpdk_remap_txqs(vhost_dev); + exists = true; + ovs_mutex_unlock(&vhost_dev->mutex); + break; } } ovs_mutex_unlock(&dpdk_mutex); - VLOG_INFO("vHost Device '%s' (%ld) has been removed", - dev->ifname, dev->device_fh); + if (exists) { + VLOG_INFO("State of queue %d ( tx_qid %d ) of vhost device '%s' %" + PRIu64" changed to \'%s\'", queue_id, qid, dev->ifname, + dev->device_fh, (enable == 1) ? "enabled" : "disabled"); + } else { + VLOG_INFO("vHost Device '%s' %"PRIu64" not found", dev->ifname, + dev->device_fh); + return -1; + } + + return 0; } struct virtio_net * @@ -1778,6 +2202,7 @@ 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 * @@ -1843,7 +2268,7 @@ dpdk_ring_create(const char dev_name[], unsigned int port_no, unsigned int *eth_port_id) { struct dpdk_ring *ivshmem; - char ring_name[10]; + char ring_name[RTE_RING_NAMESIZE]; int err; ivshmem = dpdk_rte_mzalloc(sizeof *ivshmem); @@ -1852,27 +2277,27 @@ dpdk_ring_create(const char dev_name[], unsigned int port_no, } /* XXX: Add support for multiquque ring. */ - err = snprintf(ring_name, 10, "%s_tx", dev_name); + err = snprintf(ring_name, sizeof(ring_name), "%s_tx", dev_name); if (err < 0) { return -err; } - /* Create single consumer/producer rings, netdev does explicit locking. */ + /* Create single producer tx ring, netdev does explicit locking. */ ivshmem->cring_tx = rte_ring_create(ring_name, DPDK_RING_SIZE, SOCKET0, - RING_F_SP_ENQ | RING_F_SC_DEQ); + RING_F_SP_ENQ); if (ivshmem->cring_tx == NULL) { rte_free(ivshmem); return ENOMEM; } - err = snprintf(ring_name, 10, "%s_rx", dev_name); + err = snprintf(ring_name, sizeof(ring_name), "%s_rx", dev_name); if (err < 0) { return -err; } - /* Create single consumer/producer rings, netdev does explicit locking. */ + /* Create single consumer rx ring, netdev does explicit locking. */ ivshmem->cring_rx = rte_ring_create(ring_name, DPDK_RING_SIZE, SOCKET0, - RING_F_SP_ENQ | RING_F_SC_DEQ); + RING_F_SC_DEQ); if (ivshmem->cring_rx == NULL) { rte_free(ivshmem); return ENOMEM; @@ -1931,7 +2356,7 @@ netdev_dpdk_ring_send(struct netdev *netdev_, int qid, * the consumer of the ring and return into the datapath without recalculating * the RSS hash. */ for (i = 0; i < cnt; i++) { - dp_packet_set_rss_hash(pkts[i], 0); + dp_packet_rss_invalidate(pkts[i]); } netdev_dpdk_send__(netdev, qid, pkts, cnt, may_steal); @@ -1962,6 +2387,255 @@ unlock_dpdk: return err; } +/* QoS Functions */ + +/* + * Initialize QoS configuration operations. + */ +static void +qos_conf_init(struct qos_conf *conf, const struct dpdk_qos_ops *ops) +{ + conf->ops = ops; +} + +/* + * Search existing QoS operations in qos_ops and compare each set of + * operations qos_name to name. Return a dpdk_qos_ops pointer to a match, + * else return NULL + */ +static const struct dpdk_qos_ops * +qos_lookup_name(const char *name) +{ + const struct dpdk_qos_ops *const *opsp; + + for (opsp = qos_confs; *opsp != NULL; opsp++) { + const struct dpdk_qos_ops *ops = *opsp; + if (!strcmp(name, ops->qos_name)) { + return ops; + } + } + return NULL; +} + +/* + * Call qos_destruct to clean up items associated with the netdevs + * qos_conf. Set netdevs qos_conf to NULL. + */ +static void +qos_delete_conf(struct netdev *netdev_) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + + rte_spinlock_lock(&netdev->qos_lock); + if (netdev->qos_conf) { + if (netdev->qos_conf->ops->qos_destruct) { + netdev->qos_conf->ops->qos_destruct(netdev_, netdev->qos_conf); + } + netdev->qos_conf = NULL; + } + rte_spinlock_unlock(&netdev->qos_lock); +} + +static int +netdev_dpdk_get_qos_types(const struct netdev *netdev OVS_UNUSED, + struct sset *types) +{ + const struct dpdk_qos_ops *const *opsp; + + for (opsp = qos_confs; *opsp != NULL; opsp++) { + const struct dpdk_qos_ops *ops = *opsp; + if (ops->qos_construct && ops->qos_name[0] != '\0') { + sset_add(types, ops->qos_name); + } + } + return 0; +} + +static int +netdev_dpdk_get_qos(const struct netdev *netdev_, + const char **typep, struct smap *details) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + int error = 0; + + ovs_mutex_lock(&netdev->mutex); + if(netdev->qos_conf) { + *typep = netdev->qos_conf->ops->qos_name; + error = (netdev->qos_conf->ops->qos_get + ? netdev->qos_conf->ops->qos_get(netdev_, details): 0); + } + ovs_mutex_unlock(&netdev->mutex); + + return error; +} + +static int +netdev_dpdk_set_qos(struct netdev *netdev_, + const char *type, const struct smap *details) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + const struct dpdk_qos_ops *new_ops = NULL; + int error = 0; + + /* If type is empty or unsupported then the current QoS configuration + * for the dpdk-netdev can be destroyed */ + new_ops = qos_lookup_name(type); + + if (type[0] == '\0' || !new_ops || !new_ops->qos_construct) { + qos_delete_conf(netdev_); + return EOPNOTSUPP; + } + + ovs_mutex_lock(&netdev->mutex); + + if (netdev->qos_conf) { + if (new_ops == netdev->qos_conf->ops) { + error = new_ops->qos_set ? new_ops->qos_set(netdev_, details) : 0; + } else { + /* Delete existing QoS configuration. */ + qos_delete_conf(netdev_); + ovs_assert(netdev->qos_conf == NULL); + + /* Install new QoS configuration. */ + error = new_ops->qos_construct(netdev_, details); + ovs_assert((error == 0) == (netdev->qos_conf != NULL)); + } + } else { + error = new_ops->qos_construct(netdev_, details); + ovs_assert((error == 0) == (netdev->qos_conf != NULL)); + } + + ovs_mutex_unlock(&netdev->mutex); + return error; +} + +/* egress-policer details */ + +struct egress_policer { + struct qos_conf qos_conf; + struct rte_meter_srtcm_params app_srtcm_params; + struct rte_meter_srtcm egress_meter; +}; + +static struct egress_policer * +egress_policer_get__(const struct netdev *netdev_) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + return CONTAINER_OF(netdev->qos_conf, struct egress_policer, qos_conf); +} + +static int +egress_policer_qos_construct(struct netdev *netdev_, + const struct smap *details) +{ + struct netdev_dpdk *netdev = netdev_dpdk_cast(netdev_); + struct egress_policer *policer; + const char *cir_s; + const char *cbs_s; + int err = 0; + + rte_spinlock_lock(&netdev->qos_lock); + policer = xmalloc(sizeof *policer); + qos_conf_init(&policer->qos_conf, &egress_policer_ops); + netdev->qos_conf = &policer->qos_conf; + cir_s = smap_get(details, "cir"); + cbs_s = smap_get(details, "cbs"); + policer->app_srtcm_params.cir = cir_s ? strtoull(cir_s, NULL, 10) : 0; + policer->app_srtcm_params.cbs = cbs_s ? strtoull(cbs_s, NULL, 10) : 0; + policer->app_srtcm_params.ebs = 0; + err = rte_meter_srtcm_config(&policer->egress_meter, + &policer->app_srtcm_params); + rte_spinlock_unlock(&netdev->qos_lock); + + return err; +} + +static void +egress_policer_qos_destruct(struct netdev *netdev_ OVS_UNUSED, + struct qos_conf *conf) +{ + struct egress_policer *policer = CONTAINER_OF(conf, struct egress_policer, + qos_conf); + free(policer); +} + +static int +egress_policer_qos_get(const struct netdev *netdev, struct smap *details) +{ + struct egress_policer *policer = egress_policer_get__(netdev); + smap_add_format(details, "cir", "%llu", + 1ULL * policer->app_srtcm_params.cir); + smap_add_format(details, "cbs", "%llu", + 1ULL * policer->app_srtcm_params.cbs); + return 0; +} + +static int +egress_policer_qos_set(struct netdev *netdev_, const struct smap *details) +{ + struct egress_policer *policer; + const char *cir_s; + const char *cbs_s; + int err = 0; + + policer = egress_policer_get__(netdev_); + cir_s = smap_get(details, "cir"); + cbs_s = smap_get(details, "cbs"); + policer->app_srtcm_params.cir = cir_s ? strtoull(cir_s, NULL, 10) : 0; + policer->app_srtcm_params.cbs = cbs_s ? strtoull(cbs_s, NULL, 10) : 0; + policer->app_srtcm_params.ebs = 0; + err = rte_meter_srtcm_config(&policer->egress_meter, + &policer->app_srtcm_params); + + return err; +} + +static inline bool +egress_policer_pkt_handle__(struct rte_meter_srtcm *meter, + struct rte_mbuf *pkt, uint64_t time) +{ + uint32_t pkt_len = rte_pktmbuf_pkt_len(pkt) - sizeof(struct ether_hdr); + + return rte_meter_srtcm_color_blind_check(meter, time, pkt_len) == + e_RTE_METER_GREEN; +} + +static int +egress_policer_run(struct netdev *netdev_, struct rte_mbuf **pkts, + int pkt_cnt) +{ + int i = 0; + int cnt = 0; + struct egress_policer *policer = egress_policer_get__(netdev_); + struct rte_mbuf *pkt = NULL; + uint64_t current_time = rte_rdtsc(); + + for(i = 0; i < pkt_cnt; i++) { + pkt = pkts[i]; + /* Handle current packet */ + if (egress_policer_pkt_handle__(&policer->egress_meter, pkt, + current_time)) { + if (cnt != i) { + pkts[cnt] = pkt; + } + cnt++; + } else { + rte_pktmbuf_free(pkt); + } + } + + return cnt; +} + +static const struct dpdk_qos_ops egress_policer_ops = { + "egress-policer", /* qos_name */ + egress_policer_qos_construct, + egress_policer_qos_destruct, + egress_policer_qos_get, + egress_policer_qos_set, + egress_policer_run +}; + #define NETDEV_DPDK_CLASS(NAME, INIT, CONSTRUCT, DESTRUCT, MULTIQ, SEND, \ GET_CARRIER, GET_STATS, GET_FEATURES, GET_STATUS, RXQ_RECV) \ { \ @@ -1975,7 +2649,7 @@ unlock_dpdk: DESTRUCT, \ netdev_dpdk_dealloc, \ netdev_dpdk_get_config, \ - NULL, /* netdev_dpdk_set_config */ \ + netdev_dpdk_set_config, \ NULL, /* get_tunnel_config */ \ NULL, /* build header */ \ NULL, /* push header */ \ @@ -1999,10 +2673,10 @@ unlock_dpdk: NULL, /* set_advertisements */ \ \ NULL, /* set_policing */ \ - NULL, /* get_qos_types */ \ + netdev_dpdk_get_qos_types, \ NULL, /* get_qos_capabilities */ \ - NULL, /* get_qos */ \ - NULL, /* set_qos */ \ + netdev_dpdk_get_qos, \ + netdev_dpdk_set_qos, \ NULL, /* get_queue */ \ NULL, /* set_queue */ \ NULL, /* delete_queue */ \ @@ -2041,14 +2715,14 @@ process_vhost_flags(char *flag, char *default_val, int size, * flag if it is provided on the vswitchd command line, otherwise resort to * a default value. * - * For vhost-user: Process "-cuse_dev_name" to set the custom location of + * For vhost-user: Process "-vhost_sock_dir" to set the custom location of * the vhost-user socket(s). - * For vhost-cuse: Process "-vhost_sock_dir" to set the custom name of the + * For vhost-cuse: Process "-cuse_dev_name" to set the custom name of the * vhost-cuse character device. */ if (!strcmp(argv[1], flag) && (strlen(argv[2]) <= size)) { changed = 1; - *new_val = strdup(argv[2]); + *new_val = xstrdup(argv[2]); VLOG_INFO("User-provided %s in use: %s", flag, *new_val); } else { VLOG_INFO("No %s provided - defaulting to %s", flag, default_val); @@ -2072,11 +2746,19 @@ dpdk_init(int argc, char **argv) argc--; argv++; + /* Reject --user option */ + int i; + for (i = 0; i < argc; i++) { + if (!strcmp(argv[i], "--user")) { + VLOG_ERR("Can not mix --dpdk and --user options, aborting."); + } + } + #ifdef VHOST_CUSE - if (process_vhost_flags("-cuse_dev_name", strdup("vhost-net"), + if (process_vhost_flags("-cuse_dev_name", xstrdup("vhost-net"), PATH_MAX, argv, &cuse_dev_name)) { #else - if (process_vhost_flags("-vhost_sock_dir", strdup(ovs_rundir()), + if (process_vhost_flags("-vhost_sock_dir", xstrdup(ovs_rundir()), NAME_MAX, argv, &vhost_sock_dir)) { struct stat s; int err; @@ -2155,7 +2837,7 @@ static const struct netdev_class OVS_UNUSED dpdk_vhost_cuse_class = dpdk_vhost_cuse_class_init, netdev_dpdk_vhost_cuse_construct, netdev_dpdk_vhost_destruct, - netdev_dpdk_vhost_set_multiq, + netdev_dpdk_vhost_cuse_set_multiq, netdev_dpdk_vhost_send, netdev_dpdk_vhost_get_carrier, netdev_dpdk_vhost_get_stats, @@ -2220,7 +2902,7 @@ pmd_thread_setaffinity_cpu(unsigned cpu) } static bool -thread_is_pmd(void) +dpdk_thread_is_pmd(void) { return rte_lcore_id() != NON_PMD_CORE_ID; }