/*
- * Copyright (c) 2014, 2015, 2016 Nicira, Inc.
+ * Copyright (c) 2014, 2015, 2016, 2017 Nicira, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
#include <stdlib.h>
#include <errno.h>
#include <unistd.h>
+#include <linux/virtio_net.h>
+#include <sys/socket.h>
+#include <linux/if.h>
+#include <rte_bus_pci.h>
#include <rte_config.h>
#include <rte_cycles.h>
#include <rte_errno.h>
#include <rte_malloc.h>
#include <rte_mbuf.h>
#include <rte_meter.h>
-#include <rte_virtio_net.h>
+#include <rte_pci.h>
+#include <rte_vhost.h>
+#include <rte_version.h>
#include "dirs.h"
#include "dp-packet.h"
#include "timeval.h"
#include "unixctl.h"
+enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM};
+
VLOG_DEFINE_THIS_MODULE(netdev_dpdk);
static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 20);
#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 MBUF_SIZE(mtu) ROUND_UP((MTU_TO_MAX_FRAME_LEN(mtu) \
+ + sizeof(struct dp_packet) \
+ + RTE_PKTMBUF_HEADROOM), \
+ RTE_CACHE_LINE_SIZE)
#define NETDEV_DPDK_MBUF_ALIGN 1024
#define NETDEV_DPDK_MAX_PKT_LEN 9728
-/* 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
- * enough hugepages) we keep halving the number until the allocation succeeds
- * or we reach MIN_NB_MBUF */
-
-#define MAX_NB_MBUF (4096 * 64)
+/* Min number of packets in the mempool. OVS tries to allocate a mempool with
+ * roughly estimated number of mbufs: if this fails (because the system doesn't
+ * have enough hugepages) we keep halving the number until the allocation
+ * succeeds or we reach MIN_NB_MBUF */
#define MIN_NB_MBUF (4096 * 4)
#define MP_CACHE_SZ RTE_MEMPOOL_CACHE_MAX_SIZE
-/* MAX_NB_MBUF can be divided by 2 many times, until MIN_NB_MBUF */
-BUILD_ASSERT_DECL(MAX_NB_MBUF % ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF) == 0);
-
-/* The smallest possible NB_MBUF that we're going to try should be a multiple
- * of MP_CACHE_SZ. This is advised by DPDK documentation. */
-BUILD_ASSERT_DECL((MAX_NB_MBUF / ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF))
- % MP_CACHE_SZ == 0);
-
/*
* DPDK XSTATS Counter names definition
*/
#define XSTAT_TX_1024_TO_1522_PACKETS "tx_size_1024_to_1522_packets"
#define XSTAT_TX_1523_TO_MAX_PACKETS "tx_size_1523_to_max_packets"
+#define XSTAT_RX_MULTICAST_PACKETS "rx_multicast_packets"
#define XSTAT_TX_MULTICAST_PACKETS "tx_multicast_packets"
#define XSTAT_RX_BROADCAST_PACKETS "rx_broadcast_packets"
#define XSTAT_TX_BROADCAST_PACKETS "tx_broadcast_packets"
#define OVS_VHOST_QUEUE_DISABLED (-2) /* Queue was disabled by guest and not
* yet mapped to another queue. */
+#define DPDK_ETH_PORT_ID_INVALID RTE_MAX_ETHPORTS
+
+/* DPDK library uses uint16_t for port_id. */
+typedef uint16_t dpdk_port_t;
+
#define VHOST_ENQ_RETRY_NUM 8
#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
},
};
+/*
+ * These callbacks allow virtio-net devices to be added to vhost ports when
+ * configuration has been fully completed.
+ */
+static int new_device(int vid);
+static void destroy_device(int vid);
+static int vring_state_changed(int vid, uint16_t queue_id, int enable);
+static const struct vhost_device_ops virtio_net_device_ops =
+{
+ .new_device = new_device,
+ .destroy_device = destroy_device,
+ .vring_state_changed = vring_state_changed,
+ .features_changed = NULL
+};
+
enum { DPDK_RING_SIZE = 256 };
BUILD_ASSERT_DECL(IS_POW2(DPDK_RING_SIZE));
enum { DRAIN_TSC = 200000ULL };
* For all QoS implementations it should always be non-null.
*/
int (*qos_run)(struct qos_conf *qos_conf, struct rte_mbuf **pkts,
- int pkt_cnt);
+ int pkt_cnt, bool may_steal);
};
/* dpdk_qos_ops for each type of user space QoS implementation */
static struct ovs_mutex dpdk_mp_mutex OVS_ACQ_AFTER(dpdk_mutex)
= OVS_MUTEX_INITIALIZER;
-static struct ovs_list dpdk_mp_list OVS_GUARDED_BY(dpdk_mp_mutex)
- = OVS_LIST_INITIALIZER(&dpdk_mp_list);
-
-struct dpdk_mp {
- struct rte_mempool *mp;
- int mtu;
- int socket_id;
- int refcount;
- struct ovs_list list_node OVS_GUARDED_BY(dpdk_mp_mutex);
-};
-
/* There should be one 'struct dpdk_tx_queue' created for
* each cpu core. */
struct dpdk_tx_queue {
struct rte_ring *cring_tx;
struct rte_ring *cring_rx;
unsigned int user_port_id; /* User given port no, parsed from port name */
- int eth_port_id; /* ethernet device port id */
+ dpdk_port_t eth_port_id; /* ethernet device port id */
struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex);
};
NETDEV_RX_CHECKSUM_OFFLOAD = 1 << 0,
};
-struct netdev_dpdk {
- struct netdev up;
- int port_id;
- int max_packet_len;
- enum dpdk_dev_type type;
-
- struct dpdk_tx_queue *tx_q;
-
- struct ovs_mutex mutex OVS_ACQ_AFTER(dpdk_mutex);
-
- struct dpdk_mp *dpdk_mp;
- int mtu;
- int socket_id;
- int buf_size;
- struct netdev_stats stats;
- /* Protects stats */
- rte_spinlock_t stats_lock;
-
- struct eth_addr hwaddr;
- enum netdev_flags flags;
-
- 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];
-
- /* In dpdk_list. */
- struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex);
-
- /* QoS configuration and lock for the device */
- OVSRCU_TYPE(struct qos_conf *) qos_conf;
-
- /* The following properties cannot be changed when a device is running,
- * so we remember the request and update them next time
- * netdev_dpdk*_reconfigure() is called */
- int requested_mtu;
- int requested_n_txq;
- int requested_n_rxq;
- int requested_rxq_size;
- int requested_txq_size;
-
- /* Number of rx/tx descriptors for physical devices */
- int rxq_size;
- int txq_size;
-
- /* Socket ID detected when vHost device is brought up */
- int requested_socket_id;
-
- /* Denotes whether vHost port is client/server mode */
- uint64_t vhost_driver_flags;
-
- /* Ingress Policer */
- OVSRCU_TYPE(struct ingress_policer *) ingress_policer;
- uint32_t policer_rate;
- uint32_t policer_burst;
-
- /* DPDK-ETH Flow control */
- struct rte_eth_fc_conf fc_conf;
+/*
+ * In order to avoid confusion in variables names, following naming convention
+ * should be used, if possible:
+ *
+ * 'struct netdev' : 'netdev'
+ * 'struct netdev_dpdk' : 'dev'
+ * 'struct netdev_rxq' : 'rxq'
+ * 'struct netdev_rxq_dpdk' : 'rx'
+ *
+ * Example:
+ * struct netdev *netdev = netdev_from_name(name);
+ * struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+ *
+ * Also, 'netdev' should be used instead of 'dev->up', where 'netdev' was
+ * already defined.
+ */
- /* DPDK-ETH hardware offload features,
- * from the enum set 'dpdk_hw_ol_features' */
- uint32_t hw_ol_features;
+struct netdev_dpdk {
+ PADDED_MEMBERS_CACHELINE_MARKER(CACHE_LINE_SIZE, cacheline0,
+ dpdk_port_t port_id;
+
+ /* If true, device was attached by rte_eth_dev_attach(). */
+ bool attached;
+ struct eth_addr hwaddr;
+ int mtu;
+ int socket_id;
+ int buf_size;
+ int max_packet_len;
+ enum dpdk_dev_type type;
+ enum netdev_flags flags;
+ char *devargs; /* Device arguments for dpdk ports */
+ struct dpdk_tx_queue *tx_q;
+ struct rte_eth_link link;
+ int link_reset_cnt;
+ /* 4 pad bytes here. */
+ );
+
+ PADDED_MEMBERS_CACHELINE_MARKER(CACHE_LINE_SIZE, cacheline1,
+ struct ovs_mutex mutex OVS_ACQ_AFTER(dpdk_mutex);
+ struct rte_mempool *mp;
+
+ /* virtio identifier for vhost devices */
+ ovsrcu_index vid;
+
+ /* True if vHost device is 'up' and has been reconfigured at least once */
+ bool vhost_reconfigured;
+ /* 3 pad bytes here. */
+ );
+
+ PADDED_MEMBERS(CACHE_LINE_SIZE,
+ /* Identifier used to distinguish vhost devices from each other. */
+ char vhost_id[PATH_MAX];
+ );
+
+ PADDED_MEMBERS(CACHE_LINE_SIZE,
+ struct netdev up;
+ /* In dpdk_list. */
+ struct ovs_list list_node OVS_GUARDED_BY(dpdk_mutex);
+
+ /* QoS configuration and lock for the device */
+ OVSRCU_TYPE(struct qos_conf *) qos_conf;
+
+ /* Ingress Policer */
+ OVSRCU_TYPE(struct ingress_policer *) ingress_policer;
+ uint32_t policer_rate;
+ uint32_t policer_burst;
+ );
+
+ PADDED_MEMBERS(CACHE_LINE_SIZE,
+ struct netdev_stats stats;
+ /* Protects stats */
+ rte_spinlock_t stats_lock;
+ /* 44 pad bytes here. */
+ );
+
+ PADDED_MEMBERS(CACHE_LINE_SIZE,
+ /* The following properties cannot be changed when a device is running,
+ * so we remember the request and update them next time
+ * netdev_dpdk*_reconfigure() is called */
+ int requested_mtu;
+ int requested_n_txq;
+ int requested_n_rxq;
+ int requested_rxq_size;
+ int requested_txq_size;
+
+ /* Number of rx/tx descriptors for physical devices */
+ int rxq_size;
+ int txq_size;
+
+ /* Socket ID detected when vHost device is brought up */
+ int requested_socket_id;
+
+ /* Denotes whether vHost port is client/server mode */
+ uint64_t vhost_driver_flags;
+
+ /* DPDK-ETH Flow control */
+ struct rte_eth_fc_conf fc_conf;
+
+ /* DPDK-ETH hardware offload features,
+ * from the enum set 'dpdk_hw_ol_features' */
+ uint32_t hw_ol_features;
+ );
};
struct netdev_rxq_dpdk {
struct netdev_rxq up;
- int port_id;
+ dpdk_port_t port_id;
};
-static int netdev_dpdk_class_init(void);
-static int netdev_dpdk_vhost_class_init(void);
+static void netdev_dpdk_destruct(struct netdev *netdev);
+static void netdev_dpdk_vhost_destruct(struct netdev *netdev);
int netdev_dpdk_get_vid(const struct netdev_dpdk *dev);
static bool
is_dpdk_class(const struct netdev_class *class)
{
- return class->init == netdev_dpdk_class_init
- || class->init == netdev_dpdk_vhost_class_init;
+ return class->destruct == netdev_dpdk_destruct
+ || class->destruct == netdev_dpdk_vhost_destruct;
}
/* DPDK NIC drivers allocate RX buffers at a particular granularity, typically
}
static void
-ovs_rte_pktmbuf_init(struct rte_mempool *mp,
+ovs_rte_pktmbuf_init(struct rte_mempool *mp OVS_UNUSED,
void *opaque_arg OVS_UNUSED,
void *_p,
unsigned i OVS_UNUSED)
{
struct rte_mbuf *pkt = _p;
- rte_pktmbuf_init(mp, opaque_arg, _p, i);
-
dp_packet_init_dpdk((struct dp_packet *) pkt, pkt->buf_len);
}
-static struct dpdk_mp *
-dpdk_mp_create(int socket_id, int mtu)
-{
- struct rte_pktmbuf_pool_private mbp_priv;
- struct dpdk_mp *dmp;
- unsigned mp_size;
- char *mp_name;
-
- dmp = dpdk_rte_mzalloc(sizeof *dmp);
- if (!dmp) {
- return NULL;
- }
- 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);
- /* XXX: this is a really rough method of provisioning memory.
- * It's impossible to determine what the exact memory requirements are
- * when the number of ports and rxqs that utilize a particular mempool can
- * change dynamically at runtime. For now, use this rough heurisitic.
+/* Returns a valid pointer when either of the following is true:
+ * - a new mempool was just created;
+ * - a matching mempool already exists. */
+static struct rte_mempool *
+dpdk_mp_create(struct netdev_dpdk *dev, int mtu)
+{
+ char mp_name[RTE_MEMPOOL_NAMESIZE];
+ const char *netdev_name = netdev_get_name(&dev->up);
+ int socket_id = dev->requested_socket_id;
+ uint32_t n_mbufs;
+ uint32_t hash = hash_string(netdev_name, 0);
+ struct rte_mempool *mp = NULL;
+
+ /*
+ * XXX: rough estimation of number of mbufs required for this port:
+ * <packets required to fill the device rxqs>
+ * + <packets that could be stuck on other ports txqs>
+ * + <packets in the pmd threads>
+ * + <additional memory for corner cases>
*/
- if (mtu >= ETHER_MTU) {
- mp_size = MAX_NB_MBUF;
- } else {
- mp_size = MIN_NB_MBUF;
- }
+ n_mbufs = dev->requested_n_rxq * dev->requested_rxq_size
+ + dev->requested_n_txq * dev->requested_txq_size
+ + MIN(RTE_MAX_LCORE, dev->requested_n_rxq) * NETDEV_MAX_BURST
+ + MIN_NB_MBUF;
+ ovs_mutex_lock(&dpdk_mp_mutex);
do {
- mp_name = xasprintf("ovs_mp_%d_%d_%u", dmp->mtu, dmp->socket_id,
- mp_size);
-
- 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, &mbp_priv,
- ovs_rte_pktmbuf_init, NULL,
- socket_id, 0);
- if (dmp->mp) {
- VLOG_DBG("Allocated \"%s\" mempool with %u mbufs",
- mp_name, mp_size);
- }
- free(mp_name);
- if (dmp->mp) {
- return dmp;
+ /* Full DPDK memory pool name must be unique and cannot be
+ * longer than RTE_MEMPOOL_NAMESIZE. */
+ int ret = snprintf(mp_name, RTE_MEMPOOL_NAMESIZE,
+ "ovs%08x%02d%05d%07u",
+ hash, socket_id, mtu, n_mbufs);
+ if (ret < 0 || ret >= RTE_MEMPOOL_NAMESIZE) {
+ VLOG_DBG("snprintf returned %d. "
+ "Failed to generate a mempool name for \"%s\". "
+ "Hash:0x%x, socket_id: %d, mtu:%d, mbufs:%u.",
+ ret, netdev_name, hash, socket_id, mtu, n_mbufs);
+ break;
}
- } while (rte_errno == ENOMEM && (mp_size /= 2) >= MIN_NB_MBUF);
- rte_free(dmp);
- return NULL;
-}
+ VLOG_DBG("Port %s: Requesting a mempool of %u mbufs "
+ "on socket %d for %d Rx and %d Tx queues.",
+ netdev_name, n_mbufs, socket_id,
+ dev->requested_n_rxq, dev->requested_n_txq);
-static struct dpdk_mp *
-dpdk_mp_get(int socket_id, int mtu)
-{
- struct dpdk_mp *dmp;
+ mp = rte_pktmbuf_pool_create(mp_name, n_mbufs, MP_CACHE_SZ,
+ sizeof (struct dp_packet) - sizeof (struct rte_mbuf),
+ MBUF_SIZE(mtu) - sizeof(struct dp_packet), socket_id);
- ovs_mutex_lock(&dpdk_mp_mutex);
- LIST_FOR_EACH (dmp, list_node, &dpdk_mp_list) {
- if (dmp->socket_id == socket_id && dmp->mtu == mtu) {
- dmp->refcount++;
- goto out;
+ if (mp) {
+ VLOG_DBG("Allocated \"%s\" mempool with %u mbufs",
+ mp_name, n_mbufs);
+ /* rte_pktmbuf_pool_create has done some initialization of the
+ * rte_mbuf part of each dp_packet. Some OvS specific fields
+ * of the packet still need to be initialized by
+ * ovs_rte_pktmbuf_init. */
+ rte_mempool_obj_iter(mp, ovs_rte_pktmbuf_init, NULL);
+ } else if (rte_errno == EEXIST) {
+ /* A mempool with the same name already exists. We just
+ * retrieve its pointer to be returned to the caller. */
+ mp = rte_mempool_lookup(mp_name);
+ /* As the mempool create returned EEXIST we can expect the
+ * lookup has returned a valid pointer. If for some reason
+ * that's not the case we keep track of it. */
+ VLOG_DBG("A mempool with name \"%s\" already exists at %p.",
+ mp_name, mp);
+ } else {
+ VLOG_ERR("Failed mempool \"%s\" create request of %u mbufs",
+ mp_name, n_mbufs);
}
- }
-
- dmp = dpdk_mp_create(socket_id, mtu);
- ovs_list_push_back(&dpdk_mp_list, &dmp->list_node);
+ } while (!mp && rte_errno == ENOMEM && (n_mbufs /= 2) >= MIN_NB_MBUF);
-out:
ovs_mutex_unlock(&dpdk_mp_mutex);
-
- return dmp;
+ return mp;
}
+/* Release an existing mempool. */
static void
-dpdk_mp_put(struct dpdk_mp *dmp)
+dpdk_mp_free(struct rte_mempool *mp)
{
- if (!dmp) {
+ if (!mp) {
return;
}
ovs_mutex_lock(&dpdk_mp_mutex);
- ovs_assert(dmp->refcount);
-
- if (!--dmp->refcount) {
- ovs_list_remove(&dmp->list_node);
- rte_mempool_free(dmp->mp);
- rte_free(dmp);
- }
+ VLOG_DBG("Releasing \"%s\" mempool", mp->name);
+ rte_mempool_free(mp);
ovs_mutex_unlock(&dpdk_mp_mutex);
}
-/* Tries to allocate new mempool on requested_socket_id with
- * mbuf size corresponding to requested_mtu.
- * On success new configuration will be applied.
+/* Tries to allocate a new mempool - or re-use an existing one where
+ * appropriate - on requested_socket_id with a size determined by
+ * requested_mtu and requested Rx/Tx queues.
+ * On success - or when re-using an existing mempool - the new configuration
+ * will be applied.
* On error, device will be left unchanged. */
static int
netdev_dpdk_mempool_configure(struct netdev_dpdk *dev)
OVS_REQUIRES(dev->mutex)
{
uint32_t buf_size = dpdk_buf_size(dev->requested_mtu);
- struct dpdk_mp *mp;
+ struct rte_mempool *mp;
+ int ret = 0;
- mp = dpdk_mp_get(dev->requested_socket_id, FRAME_LEN_TO_MTU(buf_size));
+ mp = dpdk_mp_create(dev, FRAME_LEN_TO_MTU(buf_size));
if (!mp) {
- VLOG_ERR("Insufficient memory to create memory pool for netdev "
- "%s, with MTU %d on socket %d\n",
- dev->up.name, dev->requested_mtu, dev->requested_socket_id);
- return ENOMEM;
+ VLOG_ERR("Failed to create memory pool for netdev "
+ "%s, with MTU %d on socket %d: %s\n",
+ dev->up.name, dev->requested_mtu, dev->requested_socket_id,
+ rte_strerror(rte_errno));
+ ret = rte_errno;
} else {
- dpdk_mp_put(dev->dpdk_mp);
- dev->dpdk_mp = mp;
+ /* If a new MTU was requested and its rounded value equals the one
+ * that is currently used, then the existing mempool is returned. */
+ if (dev->mp != mp) {
+ /* A new mempool was created, release the previous one. */
+ dpdk_mp_free(dev->mp);
+ } else {
+ ret = EEXIST;
+ }
+ dev->mp = mp;
dev->mtu = dev->requested_mtu;
dev->socket_id = dev->requested_socket_id;
dev->max_packet_len = MTU_TO_FRAME_LEN(dev->mtu);
}
- return 0;
+ return ret;
}
static void
dev->link_reset_cnt++;
dev->link = link;
if (dev->link.link_status) {
- VLOG_DBG_RL(&rl, "Port %d Link Up - speed %u Mbps - %s",
+ VLOG_DBG_RL(&rl, "Port %"PRIu8" Link Up - speed %u Mbps - %s",
dev->port_id, (unsigned) dev->link.link_speed,
(dev->link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
("full-duplex") : ("half-duplex"));
} else {
- VLOG_DBG_RL(&rl, "Port %d Link Down", dev->port_id);
+ VLOG_DBG_RL(&rl, "Port %"PRIu8" Link Down", dev->port_id);
}
}
}
int i;
struct rte_eth_conf conf = port_conf;
+ /* For some NICs (e.g. Niantic), scatter_rx mode needs to be explicitly
+ * enabled. */
if (dev->mtu > ETHER_MTU) {
- conf.rxmode.jumbo_frame = 1;
- conf.rxmode.max_rx_pkt_len = dev->max_packet_len;
- } else {
- conf.rxmode.jumbo_frame = 0;
- conf.rxmode.max_rx_pkt_len = 0;
+ conf.rxmode.enable_scatter = 1;
}
+
conf.rxmode.hw_ip_checksum = (dev->hw_ol_features &
NETDEV_RX_CHECKSUM_OFFLOAD) != 0;
/* A device may report more queues than it makes available (this has
break;
}
+ diag = rte_eth_dev_set_mtu(dev->port_id, dev->mtu);
+ if (diag) {
+ VLOG_ERR("Interface %s MTU (%d) setup error: %s",
+ dev->up.name, dev->mtu, rte_strerror(-diag));
+ break;
+ }
+
for (i = 0; i < n_txq; i++) {
diag = rte_eth_tx_queue_setup(dev->port_id, i, dev->txq_size,
dev->socket_id, NULL);
for (i = 0; i < n_rxq; i++) {
diag = rte_eth_rx_queue_setup(dev->port_id, i, dev->rxq_size,
- dev->socket_id, NULL,
- dev->dpdk_mp->mp);
+ dev->socket_id, NULL, dev->mp);
if (diag) {
VLOG_INFO("Interface %s rxq(%d) setup error: %s",
dev->up.name, i, rte_strerror(-diag));
return diag;
}
-static void
-dpdk_eth_checksum_offload_configure(struct netdev_dpdk *dev)
- OVS_REQUIRES(dev->mutex)
-{
- struct rte_eth_dev_info info;
- bool rx_csum_ol_flag = false;
- uint32_t rx_chksm_offload_capa = DEV_RX_OFFLOAD_UDP_CKSUM |
- DEV_RX_OFFLOAD_TCP_CKSUM |
- DEV_RX_OFFLOAD_IPV4_CKSUM;
- rte_eth_dev_info_get(dev->port_id, &info);
- rx_csum_ol_flag = (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD) != 0;
-
- if (rx_csum_ol_flag &&
- (info.rx_offload_capa & rx_chksm_offload_capa) !=
- rx_chksm_offload_capa) {
- VLOG_WARN_ONCE("Rx checksum offload is not supported on device %d",
- dev->port_id);
- dev->hw_ol_features &= ~NETDEV_RX_CHECKSUM_OFFLOAD;
- return;
- }
- netdev_request_reconfigure(&dev->up);
-}
-
static void
dpdk_eth_flow_ctrl_setup(struct netdev_dpdk *dev) OVS_REQUIRES(dev->mutex)
{
if (rte_eth_dev_flow_ctrl_set(dev->port_id, &dev->fc_conf)) {
- VLOG_WARN("Failed to enable flow control on device %d", dev->port_id);
+ VLOG_WARN("Failed to enable flow control on device %"PRIu8,
+ dev->port_id);
}
}
struct ether_addr eth_addr;
int diag;
int n_rxq, n_txq;
-
- if (!rte_eth_dev_is_valid_port(dev->port_id)) {
- return ENODEV;
- }
+ uint32_t rx_chksm_offload_capa = DEV_RX_OFFLOAD_UDP_CKSUM |
+ DEV_RX_OFFLOAD_TCP_CKSUM |
+ DEV_RX_OFFLOAD_IPV4_CKSUM;
rte_eth_dev_info_get(dev->port_id, &info);
+ if ((info.rx_offload_capa & rx_chksm_offload_capa) !=
+ rx_chksm_offload_capa) {
+ VLOG_WARN("Rx checksum offload is not supported on port %"PRIu8,
+ dev->port_id);
+ dev->hw_ol_features &= ~NETDEV_RX_CHECKSUM_OFFLOAD;
+ } else {
+ dev->hw_ol_features |= NETDEV_RX_CHECKSUM_OFFLOAD;
+ }
+
n_rxq = MIN(info.max_rx_queues, dev->up.n_rxq);
n_txq = MIN(info.max_tx_queues, dev->up.n_txq);
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"",
+ VLOG_INFO_RL(&rl, "Port %"PRIu8": "ETH_ADDR_FMT,
dev->port_id, ETH_ADDR_BYTES_ARGS(eth_addr.addr_bytes));
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);
+ mbp_priv = rte_mempool_get_priv(dev->mp);
dev->buf_size = mbp_priv->mbuf_data_room_size - RTE_PKTMBUF_HEADROOM;
- dev->flags = NETDEV_UP | NETDEV_PROMISC;
-
/* Get the Flow control configuration for DPDK-ETH */
diag = rte_eth_dev_flow_ctrl_get(dev->port_id, &dev->fc_conf);
if (diag) {
- VLOG_DBG("cannot get flow control parameters on port=%d, err=%d",
+ VLOG_DBG("cannot get flow control parameters on port=%"PRIu8", err=%d",
dev->port_id, diag);
}
}
static int
-netdev_dpdk_init(struct netdev *netdev, unsigned int port_no,
- enum dpdk_dev_type type)
+common_construct(struct netdev *netdev, dpdk_port_t port_no,
+ enum dpdk_dev_type type, int socket_id)
OVS_REQUIRES(dpdk_mutex)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- int sid;
- int err = 0;
ovs_mutex_init(&dev->mutex);
- ovs_mutex_lock(&dev->mutex);
rte_spinlock_init(&dev->stats_lock);
/* 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());
- }
-
- dev->socket_id = sid < 0 ? SOCKET0 : sid;
+ dev->socket_id = socket_id < 0 ? SOCKET0 : socket_id;
dev->requested_socket_id = dev->socket_id;
dev->port_id = port_no;
dev->type = type;
dev->flags = 0;
- dev->requested_mtu = dev->mtu = ETHER_MTU;
+ dev->requested_mtu = ETHER_MTU;
dev->max_packet_len = MTU_TO_FRAME_LEN(dev->mtu);
ovsrcu_index_init(&dev->vid, -1);
dev->vhost_reconfigured = false;
-
- err = netdev_dpdk_mempool_configure(dev);
- if (err) {
- goto unlock;
- }
+ dev->attached = false;
ovsrcu_init(&dev->qos_conf, NULL);
dev->policer_rate = 0;
dev->policer_burst = 0;
- netdev->n_rxq = NR_QUEUE;
- netdev->n_txq = NR_QUEUE;
- dev->requested_n_rxq = netdev->n_rxq;
- dev->requested_n_txq = netdev->n_txq;
- dev->rxq_size = NIC_PORT_DEFAULT_RXQ_SIZE;
- dev->txq_size = NIC_PORT_DEFAULT_TXQ_SIZE;
- dev->requested_rxq_size = dev->rxq_size;
- dev->requested_txq_size = dev->txq_size;
+ netdev->n_rxq = 0;
+ netdev->n_txq = 0;
+ dev->requested_n_rxq = NR_QUEUE;
+ dev->requested_n_txq = NR_QUEUE;
+ dev->requested_rxq_size = NIC_PORT_DEFAULT_RXQ_SIZE;
+ dev->requested_txq_size = NIC_PORT_DEFAULT_TXQ_SIZE;
/* Initialize the flow control to NULL */
memset(&dev->fc_conf, 0, sizeof dev->fc_conf);
/* Initilize the hardware offload flags to 0 */
dev->hw_ol_features = 0;
- if (type == DPDK_DEV_ETH) {
- 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;
- }
- if (!dev->tx_q) {
- err = ENOMEM;
- goto unlock;
- }
+ dev->flags = NETDEV_UP | NETDEV_PROMISC;
ovs_list_push_back(&dpdk_list, &dev->list_node);
-unlock:
- ovs_mutex_unlock(&dev->mutex);
- return err;
+ netdev_request_reconfigure(netdev);
+
+ return 0;
}
/* dev_name must be the prefix followed by a positive decimal number.
}
}
+static int
+vhost_common_construct(struct netdev *netdev)
+ OVS_REQUIRES(dpdk_mutex)
+{
+ int socket_id = rte_lcore_to_socket_id(rte_get_master_lcore());
+ struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+
+ dev->tx_q = netdev_dpdk_alloc_txq(OVS_VHOST_MAX_QUEUE_NUM);
+ if (!dev->tx_q) {
+ return ENOMEM;
+ }
+
+ return common_construct(netdev, DPDK_ETH_PORT_ID_INVALID,
+ DPDK_DEV_VHOST, socket_id);
+}
+
static int
netdev_dpdk_vhost_construct(struct netdev *netdev)
{
if (err) {
VLOG_ERR("vhost-user socket device setup failure for socket %s\n",
dev->vhost_id);
+ goto out;
} else {
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 = rte_vhost_driver_callback_register(dev->vhost_id,
+ &virtio_net_device_ops);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_callback_register failed for vhost user "
+ "port: %s\n", name);
+ goto out;
+ }
+
+ err = rte_vhost_driver_disable_features(dev->vhost_id,
+ 1ULL << VIRTIO_NET_F_HOST_TSO4
+ | 1ULL << VIRTIO_NET_F_HOST_TSO6
+ | 1ULL << VIRTIO_NET_F_CSUM);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user "
+ "port: %s\n", name);
+ goto out;
+ }
+
+ err = rte_vhost_driver_start(dev->vhost_id);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_start failed for vhost user "
+ "port: %s\n", name);
+ goto out;
+ }
+
+ err = vhost_common_construct(netdev);
+ if (err) {
+ VLOG_ERR("vhost_common_construct failed for vhost user "
+ "port: %s\n", name);
+ }
+
+out:
ovs_mutex_unlock(&dpdk_mutex);
+ VLOG_WARN_ONCE("dpdkvhostuser ports are considered deprecated; "
+ "please migrate to dpdkvhostuserclient ports.");
return err;
}
int err;
ovs_mutex_lock(&dpdk_mutex);
- err = netdev_dpdk_init(netdev, -1, DPDK_DEV_VHOST);
+ err = vhost_common_construct(netdev);
+ if (err) {
+ VLOG_ERR("vhost_common_construct failed for vhost user client"
+ "port: %s\n", netdev->name);
+ }
ovs_mutex_unlock(&dpdk_mutex);
return err;
}
static int
netdev_dpdk_construct(struct netdev *netdev)
{
- unsigned int port_no;
int err;
- /* Names always start with "dpdk" */
- err = dpdk_dev_parse_name(netdev->name, "dpdk", &port_no);
- if (err) {
- return err;
- }
-
ovs_mutex_lock(&dpdk_mutex);
- err = netdev_dpdk_init(netdev, port_no, DPDK_DEV_ETH);
+ err = common_construct(netdev, DPDK_ETH_PORT_ID_INVALID,
+ DPDK_DEV_ETH, SOCKET0);
ovs_mutex_unlock(&dpdk_mutex);
return err;
}
+static void
+common_destruct(struct netdev_dpdk *dev)
+ OVS_REQUIRES(dpdk_mutex)
+ OVS_EXCLUDED(dev->mutex)
+{
+ rte_free(dev->tx_q);
+ dpdk_mp_free(dev->mp);
+
+ ovs_list_remove(&dev->list_node);
+ free(ovsrcu_get_protected(struct ingress_policer *,
+ &dev->ingress_policer));
+ ovs_mutex_destroy(&dev->mutex);
+}
+
static void
netdev_dpdk_destruct(struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+ char devname[RTE_ETH_NAME_MAX_LEN];
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));
- rte_free(dev->tx_q);
- ovs_list_remove(&dev->list_node);
- dpdk_mp_put(dev->dpdk_mp);
+ if (dev->attached) {
+ rte_eth_dev_close(dev->port_id);
+ if (rte_eth_dev_detach(dev->port_id, devname) < 0) {
+ VLOG_ERR("Device '%s' can not be detached", dev->devargs);
+ } else {
+ VLOG_INFO("Device '%s' has been detached", devname);
+ }
+ }
+
+ free(dev->devargs);
+ common_destruct(dev);
- ovs_mutex_unlock(&dev->mutex);
ovs_mutex_unlock(&dpdk_mutex);
}
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
"socket '%s' must be restarted.", dev->vhost_id);
}
- 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);
- ovs_mutex_unlock(&dev->mutex);
+ common_destruct(dev);
+
ovs_mutex_unlock(&dpdk_mutex);
if (!vhost_id[0]) {
dev->txq_size);
if (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD) {
smap_add(args, "rx_csum_offload", "true");
+ } else {
+ smap_add(args, "rx_csum_offload", "false");
}
}
ovs_mutex_unlock(&dev->mutex);
return 0;
}
+static struct netdev_dpdk *
+netdev_dpdk_lookup_by_port_id(dpdk_port_t port_id)
+ OVS_REQUIRES(dpdk_mutex)
+{
+ struct netdev_dpdk *dev;
+
+ LIST_FOR_EACH (dev, list_node, &dpdk_list) {
+ if (dev->port_id == port_id) {
+ return dev;
+ }
+ }
+
+ return NULL;
+}
+
+static dpdk_port_t
+netdev_dpdk_process_devargs(struct netdev_dpdk *dev,
+ const char *devargs, char **errp)
+{
+ /* Get the name up to the first comma. */
+ char *name = xmemdup0(devargs, strcspn(devargs, ","));
+ dpdk_port_t new_port_id = DPDK_ETH_PORT_ID_INVALID;
+
+ if (rte_eth_dev_get_port_by_name(name, &new_port_id)
+ || !rte_eth_dev_is_valid_port(new_port_id)) {
+ /* Device not found in DPDK, attempt to attach it */
+ if (!rte_eth_dev_attach(devargs, &new_port_id)) {
+ /* Attach successful */
+ dev->attached = true;
+ VLOG_INFO("Device '%s' attached to DPDK", devargs);
+ } else {
+ /* Attach unsuccessful */
+ new_port_id = DPDK_ETH_PORT_ID_INVALID;
+ VLOG_WARN_BUF(errp, "Error attaching device '%s' to DPDK",
+ devargs);
+ }
+ }
+
+ free(name);
+ return new_port_id;
+}
+
static void
dpdk_set_rxq_config(struct netdev_dpdk *dev, const struct smap *args)
OVS_REQUIRES(dev->mutex)
}
static int
-netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args)
+netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args,
+ char **errp)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
bool rx_fc_en, tx_fc_en, autoneg;
{RTE_FC_NONE, RTE_FC_TX_PAUSE},
{RTE_FC_RX_PAUSE, RTE_FC_FULL }
};
- bool rx_chksm_ofld;
- bool temp_flag;
+ const char *new_devargs;
+ int err = 0;
+ ovs_mutex_lock(&dpdk_mutex);
ovs_mutex_lock(&dev->mutex);
dpdk_set_rxq_config(dev, args);
NIC_PORT_DEFAULT_TXQ_SIZE,
&dev->requested_txq_size);
+ new_devargs = smap_get(args, "dpdk-devargs");
+
+ if (dev->devargs && strcmp(new_devargs, dev->devargs)) {
+ /* The user requested a new device. If we return error, the caller
+ * will delete this netdev and try to recreate it. */
+ err = EAGAIN;
+ goto out;
+ }
+
+ /* dpdk-devargs is required for device configuration */
+ if (new_devargs && new_devargs[0]) {
+ /* Don't process dpdk-devargs if value is unchanged and port id
+ * is valid */
+ if (!(dev->devargs && !strcmp(dev->devargs, new_devargs)
+ && rte_eth_dev_is_valid_port(dev->port_id))) {
+ dpdk_port_t new_port_id = netdev_dpdk_process_devargs(dev,
+ new_devargs,
+ errp);
+ if (!rte_eth_dev_is_valid_port(new_port_id)) {
+ err = EINVAL;
+ } else if (new_port_id == dev->port_id) {
+ /* Already configured, do not reconfigure again */
+ err = 0;
+ } else {
+ struct netdev_dpdk *dup_dev;
+
+ dup_dev = netdev_dpdk_lookup_by_port_id(new_port_id);
+ if (dup_dev) {
+ VLOG_WARN_BUF(errp, "'%s' is trying to use device '%s' "
+ "which is already in use by '%s'",
+ netdev_get_name(netdev), new_devargs,
+ netdev_get_name(&dup_dev->up));
+ err = EADDRINUSE;
+ } else {
+ int sid = rte_eth_dev_socket_id(new_port_id);
+
+ dev->requested_socket_id = sid < 0 ? SOCKET0 : sid;
+ dev->devargs = xstrdup(new_devargs);
+ dev->port_id = new_port_id;
+ netdev_request_reconfigure(&dev->up);
+ err = 0;
+ }
+ }
+ }
+ } else {
+ VLOG_WARN_BUF(errp, "'%s' is missing 'options:dpdk-devargs'. "
+ "The old 'dpdk<port_id>' names are not supported",
+ netdev_get_name(netdev));
+ err = EINVAL;
+ }
+
+ if (err) {
+ goto out;
+ }
+
rx_fc_en = smap_get_bool(args, "rx-flow-ctrl", false);
tx_fc_en = smap_get_bool(args, "tx-flow-ctrl", false);
autoneg = smap_get_bool(args, "flow-ctrl-autoneg", false);
dpdk_eth_flow_ctrl_setup(dev);
}
- /* Rx checksum offload configuration */
- /* By default the Rx checksum offload is ON */
- rx_chksm_ofld = smap_get_bool(args, "rx-checksum-offload", true);
- temp_flag = (dev->hw_ol_features & NETDEV_RX_CHECKSUM_OFFLOAD)
- != 0;
- if (temp_flag != rx_chksm_ofld) {
- dev->hw_ol_features ^= NETDEV_RX_CHECKSUM_OFFLOAD;
- dpdk_eth_checksum_offload_configure(dev);
- }
+out:
ovs_mutex_unlock(&dev->mutex);
+ ovs_mutex_unlock(&dpdk_mutex);
- return 0;
+ return err;
}
static int
-netdev_dpdk_ring_set_config(struct netdev *netdev, const struct smap *args)
+netdev_dpdk_ring_set_config(struct netdev *netdev, const struct smap *args,
+ char **errp OVS_UNUSED)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
static int
netdev_dpdk_vhost_client_set_config(struct netdev *netdev,
- const struct smap *args)
+ const struct smap *args,
+ char **errp OVS_UNUSED)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
const char *path;
static int
netdev_dpdk_policer_run(struct rte_meter_srtcm *meter,
- struct rte_mbuf **pkts, int pkt_cnt)
+ struct rte_mbuf **pkts, int pkt_cnt,
+ bool may_steal)
{
int i = 0;
int cnt = 0;
}
cnt++;
} else {
- rte_pktmbuf_free(pkt);
+ if (may_steal) {
+ rte_pktmbuf_free(pkt);
+ }
}
}
static int
ingress_policer_run(struct ingress_policer *policer, struct rte_mbuf **pkts,
- int pkt_cnt)
+ int pkt_cnt, bool may_steal)
{
int cnt = 0;
rte_spinlock_lock(&policer->policer_lock);
- cnt = netdev_dpdk_policer_run(&policer->in_policer, pkts, pkt_cnt);
+ cnt = netdev_dpdk_policer_run(&policer->in_policer, pkts,
+ pkt_cnt, may_steal);
rte_spinlock_unlock(&policer->policer_lock);
return cnt;
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;
+ int qid = rxq->queue_id;
+ int vid = netdev_dpdk_get_vid(dev);
- if (OVS_UNLIKELY(!is_vhost_running(dev)
+ if (OVS_UNLIKELY(vid < 0 || !dev->vhost_reconfigured
|| !(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,
+ nb_rx = rte_vhost_dequeue_burst(vid, qid * VIRTIO_QNUM + VIRTIO_TXQ,
+ dev->mp,
(struct rte_mbuf **) batch->packets,
NETDEV_MAX_BURST);
if (!nb_rx) {
dropped = nb_rx;
nb_rx = ingress_policer_run(policer,
(struct rte_mbuf **) batch->packets,
- nb_rx);
+ nb_rx, true);
dropped -= nb_rx;
}
nb_rx, dropped);
rte_spinlock_unlock(&dev->stats_lock);
- batch->count = (int) nb_rx;
+ batch->count = nb_rx;
+ dp_packet_batch_init_packet_fields(batch);
+
return 0;
}
int nb_rx;
int dropped = 0;
+ if (OVS_UNLIKELY(!(dev->flags & NETDEV_UP))) {
+ return EAGAIN;
+ }
+
nb_rx = rte_eth_rx_burst(rx->port_id, rxq->queue_id,
(struct rte_mbuf **) batch->packets,
NETDEV_MAX_BURST);
dropped = nb_rx;
nb_rx = ingress_policer_run(policer,
(struct rte_mbuf **) batch->packets,
- nb_rx);
+ nb_rx, true);
dropped -= nb_rx;
}
}
batch->count = nb_rx;
+ dp_packet_batch_init_packet_fields(batch);
return 0;
}
static inline int
netdev_dpdk_qos_run(struct netdev_dpdk *dev, struct rte_mbuf **pkts,
- int cnt)
+ int cnt, bool may_steal)
{
struct qos_conf *qos_conf = ovsrcu_get(struct qos_conf *, &dev->qos_conf);
if (qos_conf) {
rte_spinlock_lock(&qos_conf->lock);
- cnt = qos_conf->ops->qos_run(qos_conf, pkts, cnt);
+ cnt = qos_conf->ops->qos_run(qos_conf, pkts, cnt, may_steal);
rte_spinlock_unlock(&qos_conf->lock);
}
unsigned int total_pkts = cnt;
unsigned int dropped = 0;
int i, retries = 0;
+ int vid = netdev_dpdk_get_vid(dev);
qid = dev->tx_q[qid % netdev->n_txq].map;
- if (OVS_UNLIKELY(!is_vhost_running(dev) || qid < 0
+ if (OVS_UNLIKELY(vid < 0 || !dev->vhost_reconfigured || qid < 0
|| !(dev->flags & NETDEV_UP))) {
rte_spinlock_lock(&dev->stats_lock);
dev->stats.tx_dropped+= cnt;
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);
+ cnt = netdev_dpdk_qos_run(dev, cur_pkts, cnt, true);
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);
+ tx_pkts = rte_vhost_enqueue_burst(vid, vhost_qid, cur_pkts, cnt);
if (OVS_LIKELY(tx_pkts)) {
/* Packets have been sent.*/
cnt -= tx_pkts;
dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet_batch *batch)
OVS_NO_THREAD_SAFETY_ANALYSIS
{
+ const size_t batch_cnt = dp_packet_batch_size(batch);
#if !defined(__CHECKER__) && !defined(_WIN32)
- const size_t PKT_ARRAY_SIZE = batch->count;
+ const size_t PKT_ARRAY_SIZE = batch_cnt;
#else
/* Sparse or MSVC doesn't like variable length array. */
enum { PKT_ARRAY_SIZE = NETDEV_MAX_BURST };
#endif
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
struct rte_mbuf *pkts[PKT_ARRAY_SIZE];
- int dropped = 0;
- int newcnt = 0;
- int i;
+ uint32_t cnt = batch_cnt;
+ uint32_t dropped = 0;
- dp_packet_batch_apply_cutlen(batch);
+ if (dev->type != DPDK_DEV_VHOST) {
+ /* Check if QoS has been configured for this netdev. */
+ cnt = netdev_dpdk_qos_run(dev, (struct rte_mbuf **) batch->packets,
+ batch_cnt, false);
+ dropped += batch_cnt - cnt;
+ }
- for (i = 0; i < batch->count; i++) {
- int size = dp_packet_size(batch->packets[i]);
+ uint32_t txcnt = 0;
+
+ for (uint32_t i = 0; i < cnt; i++) {
+ struct dp_packet *packet = batch->packets[i];
+ uint32_t size = dp_packet_size(packet);
if (OVS_UNLIKELY(size > dev->max_packet_len)) {
- VLOG_WARN_RL(&rl, "Too big size %d max_packet_len %d",
- (int) size, dev->max_packet_len);
+ VLOG_WARN_RL(&rl, "Too big size %u max_packet_len %d",
+ size, dev->max_packet_len);
dropped++;
continue;
}
- pkts[newcnt] = rte_pktmbuf_alloc(dev->dpdk_mp->mp);
-
- if (!pkts[newcnt]) {
- dropped += batch->count - i;
+ pkts[txcnt] = rte_pktmbuf_alloc(dev->mp);
+ if (OVS_UNLIKELY(!pkts[txcnt])) {
+ dropped += cnt - i;
break;
}
/* We have to do a copy for now */
- memcpy(rte_pktmbuf_mtod(pkts[newcnt], void *),
- dp_packet_data(batch->packets[i]), size);
-
- rte_pktmbuf_data_len(pkts[newcnt]) = size;
- rte_pktmbuf_pkt_len(pkts[newcnt]) = size;
+ memcpy(rte_pktmbuf_mtod(pkts[txcnt], void *),
+ dp_packet_data(packet), size);
+ dp_packet_set_size((struct dp_packet *)pkts[txcnt], size);
- newcnt++;
+ txcnt++;
}
- if (dev->type == DPDK_DEV_VHOST) {
- __netdev_dpdk_vhost_send(netdev, qid, (struct dp_packet **) pkts,
- newcnt);
- } else {
- unsigned int qos_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);
+ if (OVS_LIKELY(txcnt)) {
+ if (dev->type == DPDK_DEV_VHOST) {
+ __netdev_dpdk_vhost_send(netdev, qid, (struct dp_packet **) pkts,
+ txcnt);
+ } else {
+ dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, txcnt);
+ }
}
if (OVS_UNLIKELY(dropped)) {
static int
netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
struct dp_packet_batch *batch,
- bool may_steal, bool concurrent_txq OVS_UNUSED)
+ bool concurrent_txq OVS_UNUSED)
{
- if (OVS_UNLIKELY(!may_steal || batch->packets[0]->source != DPBUF_DPDK)) {
+ if (OVS_UNLIKELY(batch->packets[0]->source != DPBUF_DPDK)) {
dpdk_do_tx_copy(netdev, qid, batch);
- dp_packet_delete_batch(batch, may_steal);
+ dp_packet_delete_batch(batch, true);
} 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,
+ struct dp_packet_batch *batch,
bool concurrent_txq)
{
+ if (OVS_UNLIKELY(!(dev->flags & NETDEV_UP))) {
+ dp_packet_delete_batch(batch, true);
+ return;
+ }
+
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)) {
+ if (OVS_UNLIKELY(batch->packets[0]->source != DPBUF_DPDK)) {
struct netdev *netdev = &dev->up;
dpdk_do_tx_copy(netdev, qid, batch);
- dp_packet_delete_batch(batch, may_steal);
+ dp_packet_delete_batch(batch, true);
} else {
- int dropped;
- int cnt = batch->count;
+ int tx_cnt, dropped;
+ int batch_cnt = dp_packet_batch_size(batch);
struct rte_mbuf **pkts = (struct rte_mbuf **) batch->packets;
- dp_packet_batch_apply_cutlen(batch);
+ tx_cnt = netdev_dpdk_filter_packet_len(dev, pkts, batch_cnt);
+ tx_cnt = netdev_dpdk_qos_run(dev, pkts, tx_cnt, true);
+ dropped = batch_cnt - tx_cnt;
- cnt = netdev_dpdk_filter_packet_len(dev, pkts, cnt);
- cnt = netdev_dpdk_qos_run(dev, pkts, cnt);
- dropped = batch->count - cnt;
-
- dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, cnt);
+ dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, tx_cnt);
if (OVS_UNLIKELY(dropped)) {
rte_spinlock_lock(&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 dp_packet_batch *batch, bool concurrent_txq)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- netdev_dpdk_send__(dev, qid, batch, may_steal, concurrent_txq);
+ netdev_dpdk_send__(dev, qid, batch, concurrent_txq);
return 0;
}
rte_spinlock_lock(&dev->stats_lock);
/* Supported Stats */
- stats->rx_packets += dev->stats.rx_packets;
- stats->tx_packets += dev->stats.tx_packets;
+ 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->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->tx_1024_to_1522_packets = xstats[i].value;
} else if (strcmp(XSTAT_TX_1523_TO_MAX_PACKETS, names[i].name) == 0) {
stats->tx_1523_to_max_packets = xstats[i].value;
+ } else if (strcmp(XSTAT_RX_MULTICAST_PACKETS, names[i].name) == 0) {
+ stats->multicast = xstats[i].value;
} else if (strcmp(XSTAT_TX_MULTICAST_PACKETS, names[i].name) == 0) {
stats->tx_multicast_packets = xstats[i].value;
} else if (strcmp(XSTAT_RX_BROADCAST_PACKETS, names[i].name) == 0) {
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);
+ VLOG_ERR("Can't get ETH statistics for port: %"PRIu8, 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);
+ VLOG_WARN("Cannot get XSTATS values for port: %"PRIu8, dev->port_id);
goto out;
}
/* Reserve memory for xstats names and values */
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);
+ VLOG_WARN("Cannot get XSTATS names for port: %"PRIu8, dev->port_id);
goto out;
}
/* Retreive xstats values */
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);
+ VLOG_WARN("Cannot get XSTATS values for port: %"PRIu8, dev->port_id);
}
out:
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->rx_errors = rte_stats.ierrors;
stats->tx_errors = rte_stats.oerrors;
rte_spinlock_lock(&dev->stats_lock);
rte_spinlock_init(&policer->policer_lock);
/* rte_meter requires bytes so convert kbits rate and burst to bytes. */
- rate_bytes = rate * 1000/8;
- burst_bytes = burst * 1000/8;
+ rate_bytes = rate * 1000ULL / 8;
+ burst_bytes = burst * 1000ULL / 8;
policer->app_srtcm_params.cir = rate_bytes;
policer->app_srtcm_params.cbs = burst_bytes;
netdev_dpdk_get_ifindex(const struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- int ifindex;
ovs_mutex_lock(&dev->mutex);
- ifindex = dev->port_id;
+ /* Calculate hash from the netdev name. Ensure that ifindex is a 24-bit
+ * postive integer to meet RFC 2863 recommendations.
+ */
+ int ifindex = hash_string(netdev->name, 0) % 0xfffffe + 1;
ovs_mutex_unlock(&dev->mutex);
return ifindex;
enum netdev_flags *old_flagsp)
OVS_REQUIRES(dev->mutex)
{
- int err;
-
if ((off | on) & ~(NETDEV_UP | NETDEV_PROMISC)) {
return EINVAL;
}
}
if (dev->type == DPDK_DEV_ETH) {
- if (dev->flags & NETDEV_UP) {
- err = rte_eth_dev_start(dev->port_id);
- if (err)
- return -err;
- }
-
if (dev->flags & NETDEV_PROMISC) {
rte_eth_promiscuous_enable(dev->port_id);
}
- if (!(dev->flags & NETDEV_UP)) {
- rte_eth_dev_stop(dev->port_id);
- }
-
netdev_change_seq_changed(&dev->up);
} else {
/* If DPDK_DEV_VHOST device's NETDEV_UP flag was changed and vhost is
smap_add_format(args, "max_vfs", "%u", dev_info.max_vfs);
smap_add_format(args, "max_vmdq_pools", "%u", dev_info.max_vmdq_pools);
+ /* Querying the DPDK library for iftype may be done in future, pending
+ * support; cf. RFC 3635 Section 3.2.4. */
+ enum { IF_TYPE_ETHERNETCSMACD = 6 };
+
+ smap_add_format(args, "if_type", "%"PRIu32, IF_TYPE_ETHERNETCSMACD);
+ smap_add_format(args, "if_descr", "%s %s", rte_version(),
+ dev_info.driver_name);
+
if (dev_info.pci_dev) {
smap_add_format(args, "pci-vendor_id", "0x%u",
dev_info.pci_dev->id.vendor_id);
if (argc > 2) {
struct netdev *netdev = netdev_from_name(argv[1]);
+
if (netdev && is_dpdk_class(netdev->netdev_class)) {
- struct netdev_dpdk *dpdk_dev = netdev_dpdk_cast(netdev);
+ struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- ovs_mutex_lock(&dpdk_dev->mutex);
- netdev_dpdk_set_admin_state__(dpdk_dev, up);
- ovs_mutex_unlock(&dpdk_dev->mutex);
+ ovs_mutex_lock(&dev->mutex);
+ netdev_dpdk_set_admin_state__(dev, up);
+ ovs_mutex_unlock(&dev->mutex);
netdev_close(netdev);
} else {
return;
}
} else {
- struct netdev_dpdk *netdev;
+ struct netdev_dpdk *dev;
ovs_mutex_lock(&dpdk_mutex);
- LIST_FOR_EACH (netdev, list_node, &dpdk_list) {
- ovs_mutex_lock(&netdev->mutex);
- netdev_dpdk_set_admin_state__(netdev, up);
- ovs_mutex_unlock(&netdev->mutex);
+ LIST_FOR_EACH (dev, list_node, &dpdk_list) {
+ ovs_mutex_lock(&dev->mutex);
+ netdev_dpdk_set_admin_state__(dev, up);
+ ovs_mutex_unlock(&dev->mutex);
}
ovs_mutex_unlock(&dpdk_mutex);
}
unixctl_command_reply(conn, "OK");
}
+static void
+netdev_dpdk_detach(struct unixctl_conn *conn, int argc OVS_UNUSED,
+ const char *argv[], void *aux OVS_UNUSED)
+{
+ int ret;
+ char *response;
+ dpdk_port_t port_id;
+ char devname[RTE_ETH_NAME_MAX_LEN];
+ struct netdev_dpdk *dev;
+
+ ovs_mutex_lock(&dpdk_mutex);
+
+ if (rte_eth_dev_get_port_by_name(argv[1], &port_id)) {
+ response = xasprintf("Device '%s' not found in DPDK", argv[1]);
+ goto error;
+ }
+
+ dev = netdev_dpdk_lookup_by_port_id(port_id);
+ if (dev) {
+ response = xasprintf("Device '%s' is being used by interface '%s'. "
+ "Remove it before detaching",
+ argv[1], netdev_get_name(&dev->up));
+ goto error;
+ }
+
+ rte_eth_dev_close(port_id);
+
+ ret = rte_eth_dev_detach(port_id, devname);
+ if (ret < 0) {
+ response = xasprintf("Device '%s' can not be detached", argv[1]);
+ goto error;
+ }
+
+ response = xasprintf("Device '%s' has been detached", argv[1]);
+
+ ovs_mutex_unlock(&dpdk_mutex);
+ unixctl_command_reply(conn, response);
+ free(response);
+ return;
+
+error:
+ ovs_mutex_unlock(&dpdk_mutex);
+ unixctl_command_reply_error(conn, response);
+ free(response);
+}
+
+static void
+netdev_dpdk_get_mempool_info(struct unixctl_conn *conn,
+ int argc, const char *argv[],
+ void *aux OVS_UNUSED)
+{
+ size_t size;
+ FILE *stream;
+ char *response = NULL;
+ struct netdev *netdev = NULL;
+
+ if (argc == 2) {
+ netdev = netdev_from_name(argv[1]);
+ if (!netdev || !is_dpdk_class(netdev->netdev_class)) {
+ unixctl_command_reply_error(conn, "Not a DPDK Interface");
+ goto out;
+ }
+ }
+
+ stream = open_memstream(&response, &size);
+ if (!stream) {
+ response = xasprintf("Unable to open memstream: %s.",
+ ovs_strerror(errno));
+ unixctl_command_reply_error(conn, response);
+ goto out;
+ }
+
+ if (netdev) {
+ struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+
+ ovs_mutex_lock(&dev->mutex);
+ ovs_mutex_lock(&dpdk_mp_mutex);
+
+ rte_mempool_dump(stream, dev->mp);
+
+ ovs_mutex_unlock(&dpdk_mp_mutex);
+ ovs_mutex_unlock(&dev->mutex);
+ } else {
+ ovs_mutex_lock(&dpdk_mp_mutex);
+ rte_mempool_list_dump(stream);
+ ovs_mutex_unlock(&dpdk_mp_mutex);
+ }
+
+ fclose(stream);
+
+ unixctl_command_reply(conn, response);
+out:
+ free(response);
+ netdev_close(netdev);
+}
+
/*
* Set virtqueue flags so that we do not receive interrupts.
*/
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);
+ for (i = 0; i < rte_vhost_get_vring_num(vid); i++) {
+ rte_vhost_enable_guest_notification(vid, i, 0);
}
}
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);
+ uint32_t qp_num = rte_vhost_get_vring_num(vid)/VIRTIO_QNUM;
/* Get NUMA information */
newnode = rte_vhost_get_numa_node(vid);
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)
{
"[netdev] up|down", 1, 2,
netdev_dpdk_set_admin_state, NULL);
- ovsthread_once_done(&once);
- }
-
- return 0;
-}
-
-static int
-netdev_dpdk_vhost_class_init(void)
-{
- static struct ovsthread_once once = OVSTHREAD_ONCE_INITIALIZER;
+ unixctl_command_register("netdev-dpdk/detach",
+ "pci address of device", 1, 1,
+ netdev_dpdk_detach, NULL);
- /* 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
- | 1ULL << VIRTIO_RING_F_INDIRECT_DESC);
- ovs_thread_create("vhost_thread", start_vhost_loop, NULL);
+ unixctl_command_register("netdev-dpdk/get-mempool-info",
+ "[netdev]", 0, 1,
+ netdev_dpdk_get_mempool_info, NULL);
ovsthread_once_done(&once);
}
return 0;
}
+
/* Client Rings */
static int
dpdk_ring_create(const char dev_name[], unsigned int port_no,
- unsigned int *eth_port_id)
+ dpdk_port_t *eth_port_id)
{
struct dpdk_ring *ring_pair;
char *ring_name;
- int err;
+ int port_id;
ring_pair = dpdk_rte_mzalloc(sizeof *ring_pair);
if (!ring_pair) {
return ENOMEM;
}
- err = rte_eth_from_rings(dev_name, &ring_pair->cring_rx, 1,
- &ring_pair->cring_tx, 1, SOCKET0);
+ port_id = rte_eth_from_rings(dev_name, &ring_pair->cring_rx, 1,
+ &ring_pair->cring_tx, 1, SOCKET0);
- if (err < 0) {
+ if (port_id < 0) {
rte_free(ring_pair);
return ENODEV;
}
ring_pair->user_port_id = port_no;
- ring_pair->eth_port_id = rte_eth_dev_count() - 1;
+ ring_pair->eth_port_id = port_id;
+ *eth_port_id = port_id;
+
ovs_list_push_back(&dpdk_ring_list, &ring_pair->list_node);
- *eth_port_id = ring_pair->eth_port_id;
return 0;
}
static int
-dpdk_ring_open(const char dev_name[], unsigned int *eth_port_id)
+dpdk_ring_open(const char dev_name[], dpdk_port_t *eth_port_id)
OVS_REQUIRES(dpdk_mutex)
{
struct dpdk_ring *ring_pair;
static int
netdev_dpdk_ring_send(struct netdev *netdev, int qid,
- struct dp_packet_batch *batch, bool may_steal,
- bool concurrent_txq)
+ struct dp_packet_batch *batch, bool concurrent_txq)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- unsigned i;
+ struct dp_packet *packet;
/* When using 'dpdkr' and sending to a DPDK ring, we want to ensure that
* the rss hash field is clear. This is because the same mbuf may be
* modified by the consumer of the ring and return into the datapath
* without recalculating the RSS hash. */
- for (i = 0; i < batch->count; i++) {
- dp_packet_rss_invalidate(batch->packets[i]);
+ DP_PACKET_BATCH_FOR_EACH (packet, batch) {
+ dp_packet_mbuf_rss_flag_reset(packet);
}
- netdev_dpdk_send__(dev, qid, batch, may_steal, concurrent_txq);
+ netdev_dpdk_send__(dev, qid, batch, concurrent_txq);
return 0;
}
static int
netdev_dpdk_ring_construct(struct netdev *netdev)
{
- unsigned int port_no = 0;
+ dpdk_port_t port_no = 0;
int err = 0;
ovs_mutex_lock(&dpdk_mutex);
goto unlock_dpdk;
}
- err = netdev_dpdk_init(netdev, port_no, DPDK_DEV_ETH);
-
+ err = common_construct(netdev, port_no, DPDK_DEV_ETH,
+ rte_eth_dev_socket_id(port_no));
unlock_dpdk:
ovs_mutex_unlock(&dpdk_mutex);
return err;
}
static bool
-egress_policer_qos_is_equal(const struct qos_conf *conf, const struct smap *details)
+egress_policer_qos_is_equal(const struct qos_conf *conf,
+ const struct smap *details)
{
struct egress_policer *policer =
CONTAINER_OF(conf, struct egress_policer, qos_conf);
}
static int
-egress_policer_run(struct qos_conf *conf, struct rte_mbuf **pkts, int pkt_cnt)
+egress_policer_run(struct qos_conf *conf, struct rte_mbuf **pkts, int pkt_cnt,
+ bool may_steal)
{
int cnt = 0;
struct egress_policer *policer =
CONTAINER_OF(conf, struct egress_policer, qos_conf);
- cnt = netdev_dpdk_policer_run(&policer->egress_meter, pkts, pkt_cnt);
+ cnt = netdev_dpdk_policer_run(&policer->egress_meter, pkts,
+ pkt_cnt, may_steal);
return cnt;
}
&& netdev->n_rxq == dev->requested_n_rxq
&& dev->mtu == dev->requested_mtu
&& dev->rxq_size == dev->requested_rxq_size
- && dev->txq_size == dev->requested_txq_size) {
+ && dev->txq_size == dev->requested_txq_size
+ && dev->socket_id == dev->requested_socket_id) {
/* Reconfiguration is unnecessary */
goto out;
rte_eth_dev_stop(dev->port_id);
- if (dev->mtu != dev->requested_mtu) {
- netdev_dpdk_mempool_configure(dev);
+ err = netdev_dpdk_mempool_configure(dev);
+ if (err && err != EEXIST) {
+ goto out;
}
netdev->n_txq = dev->requested_n_txq;
return err;
}
-static void
+static int
dpdk_vhost_reconfigure_helper(struct netdev_dpdk *dev)
OVS_REQUIRES(dev->mutex)
{
dev->up.n_txq = dev->requested_n_txq;
dev->up.n_rxq = dev->requested_n_rxq;
+ int err;
/* Enable TX queue 0 by default if it wasn't disabled. */
if (dev->tx_q[0].map == OVS_VHOST_QUEUE_MAP_UNKNOWN) {
netdev_dpdk_remap_txqs(dev);
- if (dev->requested_socket_id != dev->socket_id
- || dev->requested_mtu != dev->mtu) {
- if (!netdev_dpdk_mempool_configure(dev)) {
+ err = netdev_dpdk_mempool_configure(dev);
+ if (!err) {
+ /* A new mempool was created. */
+ netdev_change_seq_changed(&dev->up);
+ } else if (err != EEXIST){
+ return err;
+ }
+ if (netdev_dpdk_get_vid(dev) >= 0) {
+ if (dev->vhost_reconfigured == false) {
+ dev->vhost_reconfigured = true;
+ /* Carrier status may need updating. */
netdev_change_seq_changed(&dev->up);
}
}
- if (netdev_dpdk_get_vid(dev) >= 0) {
- dev->vhost_reconfigured = true;
- }
+ return 0;
}
static int
netdev_dpdk_vhost_reconfigure(struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+ int err;
ovs_mutex_lock(&dev->mutex);
- dpdk_vhost_reconfigure_helper(dev);
+ err = dpdk_vhost_reconfigure_helper(dev);
ovs_mutex_unlock(&dev->mutex);
- return 0;
+
+ return err;
}
static int
netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- int err = 0;
+ int err;
+ uint64_t vhost_flags = 0;
ovs_mutex_lock(&dev->mutex);
- dpdk_vhost_reconfigure_helper(dev);
-
/* Configure vHost client mode if requested and if the following criteria
* are met:
* 1. Device hasn't been registered yet.
*/
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);
+ /* Register client-mode device. */
+ vhost_flags |= RTE_VHOST_USER_CLIENT;
+
+ /* Enable IOMMU support, if explicitly requested. */
+ if (dpdk_vhost_iommu_enabled()) {
+ vhost_flags |= RTE_VHOST_USER_IOMMU_SUPPORT;
+ }
+ err = rte_vhost_driver_register(dev->vhost_id, vhost_flags);
if (err) {
VLOG_ERR("vhost-user device setup failure for device %s\n",
dev->vhost_id);
+ goto unlock;
} else {
/* Configuration successful */
- dev->vhost_driver_flags |= RTE_VHOST_USER_CLIENT;
+ dev->vhost_driver_flags |= vhost_flags;
VLOG_INFO("vHost User device '%s' created in 'client' mode, "
"using client socket '%s'",
dev->up.name, dev->vhost_id);
}
+
+ err = rte_vhost_driver_callback_register(dev->vhost_id,
+ &virtio_net_device_ops);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_callback_register failed for "
+ "vhost user client port: %s\n", dev->up.name);
+ goto unlock;
+ }
+
+ err = rte_vhost_driver_disable_features(dev->vhost_id,
+ 1ULL << VIRTIO_NET_F_HOST_TSO4
+ | 1ULL << VIRTIO_NET_F_HOST_TSO6
+ | 1ULL << VIRTIO_NET_F_CSUM);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_disable_features failed for vhost user "
+ "client port: %s\n", dev->up.name);
+ goto unlock;
+ }
+
+ err = rte_vhost_driver_start(dev->vhost_id);
+ if (err) {
+ VLOG_ERR("rte_vhost_driver_start failed for vhost user "
+ "client port: %s\n", dev->up.name);
+ goto unlock;
+ }
}
+ err = dpdk_vhost_reconfigure_helper(dev);
+
+unlock:
ovs_mutex_unlock(&dev->mutex);
- return 0;
+ return err;
}
#define NETDEV_DPDK_CLASS(NAME, INIT, CONSTRUCT, DESTRUCT, \
GET_STATS, \
GET_FEATURES, \
NULL, /* set_advertisements */ \
+ NULL, /* get_pt_mode */ \
\
netdev_dpdk_set_policing, \
netdev_dpdk_get_qos_types, \
RXQ_RECV, \
NULL, /* rx_wait */ \
NULL, /* rxq_drain */ \
+ NO_OFFLOAD_API \
}
static const struct netdev_class dpdk_class =
static const struct netdev_class dpdk_vhost_class =
NETDEV_DPDK_CLASS(
"dpdkvhostuser",
- netdev_dpdk_vhost_class_init,
+ NULL,
netdev_dpdk_vhost_construct,
netdev_dpdk_vhost_destruct,
NULL,
static const struct netdev_class dpdk_vhost_client_class =
NETDEV_DPDK_CLASS(
"dpdkvhostuserclient",
- netdev_dpdk_vhost_class_init,
+ NULL,
netdev_dpdk_vhost_client_construct,
netdev_dpdk_vhost_destruct,
netdev_dpdk_vhost_client_set_config,