Upgrading to DPDK 17.05.1 stable release adds new significant features relevant to OVS, including, but not limited to: - tun/tap PMD, - VFIO hotplug support, - Generic flow API.
Following changes are applied: - netdev-dpdk: Changes required by DPDK API modifications. - doc: Because of DPDK API changes, backward compatibility with previous DPDK releases will be broken, thus all relevant documentation entries are updated. - .travis: DPDK version change from 16.11.1 to 17.05.1. - rhel/openvswitch-fedora.spec.in: DPDK version change from 16.11 to 17.05.1 v1->v2: Patch rebase. v2->v3: Fixed wrong formating after v2 patch rebase. v3->v4: Minor documentation changes. Signed-off-by: Michal Weglicki <michalx.wegli...@intel.com> Reviewed-by: Aaron Conole <acon...@redhat.com> --- .travis/linux-build.sh | 2 +- Documentation/faq/releases.rst | 1 + Documentation/howto/dpdk.rst | 6 +- Documentation/intro/install/dpdk.rst | 14 +-- Documentation/topics/dpdk/vhost-user.rst | 12 +-- NEWS | 1 + lib/netdev-dpdk.c | 144 +++++++++++++++++++------------ rhel/openvswitch-fedora.spec.in | 2 +- tests/dpdk/ring_client.c | 6 +- 9 files changed, 114 insertions(+), 74 deletions(-) diff --git a/.travis/linux-build.sh b/.travis/linux-build.sh index f66b534..efccdf1 100755 --- a/.travis/linux-build.sh +++ b/.travis/linux-build.sh @@ -80,7 +80,7 @@ fi if [ "$DPDK" ]; then if [ -z "$DPDK_VER" ]; then - DPDK_VER="16.11.2" + DPDK_VER="17.05.1" fi install_dpdk $DPDK_VER if [ "$CC" = "clang" ]; then diff --git a/Documentation/faq/releases.rst b/Documentation/faq/releases.rst index 707834b..2ecc24c 100644 --- a/Documentation/faq/releases.rst +++ b/Documentation/faq/releases.rst @@ -161,6 +161,7 @@ Q: What DPDK version does each Open vSwitch release work with? 2.5.x 2.2 2.6.x 16.07.2 2.7.x 16.11.2 + 2.8.x 17.05.1 ============ ======= Q: I get an error like this when I configure Open vSwitch: diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst index af01d3e..1756c8c 100644 --- a/Documentation/howto/dpdk.rst +++ b/Documentation/howto/dpdk.rst @@ -528,15 +528,15 @@ described in :ref:`dpdk-testpmd`. Once compiled, run the application:: When you finish testing, bind the vNICs back to kernel:: - $ $DPDK_DIR/tools/dpdk-devbind.py --bind=virtio-pci 0000:00:03.0 - $ $DPDK_DIR/tools/dpdk-devbind.py --bind=virtio-pci 0000:00:04.0 + $ $DPDK_DIR/usertools/dpdk-devbind.py --bind=virtio-pci 0000:00:03.0 + $ $DPDK_DIR/usertools/dpdk-devbind.py --bind=virtio-pci 0000:00:04.0 .. note:: Valid PCI IDs must be passed in above example. The PCI IDs can be retrieved like so:: - $ $DPDK_DIR/tools/dpdk-devbind.py --status + $ $DPDK_DIR/usertools/dpdk-devbind.py --status More information on the dpdkvhostuser ports can be found in :doc:`/topics/dpdk/vhost-user`. diff --git a/Documentation/intro/install/dpdk.rst b/Documentation/intro/install/dpdk.rst index a05aa1a..20baa63 100644 --- a/Documentation/intro/install/dpdk.rst +++ b/Documentation/intro/install/dpdk.rst @@ -40,7 +40,7 @@ Build requirements In addition to the requirements described in :doc:`general`, building Open vSwitch with DPDK will require the following: -- DPDK 16.11 +- DPDK 17.05.1 - A `DPDK supported NIC`_ @@ -69,9 +69,9 @@ Install DPDK #. Download the `DPDK sources`_, extract the file and set ``DPDK_DIR``:: $ cd /usr/src/ - $ wget http://fast.dpdk.org/rel/dpdk-16.11.2.tar.xz - $ tar xf dpdk-16.11.2.tar.xz - $ export DPDK_DIR=/usr/src/dpdk-stable-16.11.2 + $ wget http://fast.dpdk.org/rel/dpdk-17.05.1.tar.xz + $ tar xf dpdk-17.05.1.tar.xz + $ export DPDK_DIR=/usr/src/dpdk-stable-17.05.1 $ cd $DPDK_DIR #. (Optional) Configure DPDK as a shared library @@ -187,8 +187,8 @@ to the VFIO driver:: $ modprobe vfio-pci $ /usr/bin/chmod a+x /dev/vfio $ /usr/bin/chmod 0666 /dev/vfio/* - $ $DPDK_DIR/tools/dpdk-devbind.py --bind=vfio-pci eth1 - $ $DPDK_DIR/tools/dpdk-devbind.py --status + $ $DPDK_DIR/usertools/dpdk-devbind.py --bind=vfio-pci eth1 + $ $DPDK_DIR/usertools/dpdk-devbind.py --status Setup OVS ~~~~~~~~~ @@ -569,7 +569,7 @@ Limitations The latest list of validated firmware versions can be found in the `DPDK release notes`_. -.. _DPDK release notes: http://dpdk.org/doc/guides/rel_notes/release_16_11.html +.. _DPDK release notes: http://dpdk.org/doc/guides/rel_notes/release_17_05.html Reporting Bugs -------------- diff --git a/Documentation/topics/dpdk/vhost-user.rst b/Documentation/topics/dpdk/vhost-user.rst index e76da5f..a3d5de3 100644 --- a/Documentation/topics/dpdk/vhost-user.rst +++ b/Documentation/topics/dpdk/vhost-user.rst @@ -292,9 +292,9 @@ To begin, instantiate a guest as described in :ref:`dpdk-vhost-user` or DPDK sources to VM and build DPDK:: $ cd /root/dpdk/ - $ wget http://fast.dpdk.org/rel/dpdk-16.11.2.tar.xz - $ tar xf dpdk-16.11.2.tar.xz - $ export DPDK_DIR=/root/dpdk/dpdk-stable-16.11.2 + $ wget http://fast.dpdk.org/rel/dpdk-17.05.1.tar.xz + $ tar xf dpdk-17.05.1.tar.xz + $ export DPDK_DIR=/root/dpdk/dpdk-stable-17.05.1 $ export DPDK_TARGET=x86_64-native-linuxapp-gcc $ export DPDK_BUILD=$DPDK_DIR/$DPDK_TARGET $ cd $DPDK_DIR @@ -314,8 +314,8 @@ Setup huge pages and DPDK devices using UIO:: $ mount -t hugetlbfs hugetlbfs /dev/hugepages # only if not already mounted $ modprobe uio $ insmod $DPDK_BUILD/kmod/igb_uio.ko - $ $DPDK_DIR/tools/dpdk-devbind.py --status - $ $DPDK_DIR/tools/dpdk-devbind.py -b igb_uio 00:03.0 00:04.0 + $ $DPDK_DIR/usertools/dpdk-devbind.py --status + $ $DPDK_DIR/usertools/dpdk-devbind.py -b igb_uio 00:03.0 00:04.0 .. note:: @@ -378,7 +378,7 @@ Sample XML </disk> <disk type='dir' device='disk'> <driver name='qemu' type='fat'/> - <source dir='/usr/src/dpdk-stable-16.11.2'/> + <source dir='/usr/src/dpdk-stable-17.05.1'/> <target dev='vdb' bus='virtio'/> <readonly/> </disk> diff --git a/NEWS b/NEWS index d61fc5f..3f58e8b 100644 --- a/NEWS +++ b/NEWS @@ -21,6 +21,7 @@ Post-v2.7.0 still can be configured via extra arguments for DPDK EAL. * dpdkvhostuser ports are marked as deprecated. They will be removed in an upcoming release. + * Support for DPDK v17.05.1. - IPFIX now provides additional counters: * Total counters since metering process startup. * Per-flow TCP flag counters. diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c index ea17b97..5e767e1 100644 --- a/lib/netdev-dpdk.c +++ b/lib/netdev-dpdk.c @@ -22,6 +22,9 @@ #include <stdlib.h> #include <errno.h> #include <unistd.h> +#include <linux/virtio_net.h> +#include <sys/socket.h> +#include <linux/if.h> #include <rte_config.h> #include <rte_cycles.h> @@ -31,7 +34,7 @@ #include <rte_malloc.h> #include <rte_mbuf.h> #include <rte_meter.h> -#include <rte_virtio_net.h> +#include <rte_vhost.h> #include "dirs.h" #include "dp-packet.h" @@ -56,6 +59,8 @@ #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); @@ -171,6 +176,21 @@ static const struct rte_eth_conf port_conf = { }, }; +/* + * 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 }; @@ -412,8 +432,8 @@ struct netdev_rxq_dpdk { 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); @@ -423,8 +443,8 @@ netdev_dpdk_get_ingress_policer(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 @@ -948,13 +968,45 @@ 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 = 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."); @@ -968,6 +1020,10 @@ netdev_dpdk_vhost_client_construct(struct netdev *netdev) ovs_mutex_lock(&dpdk_mutex); 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; } @@ -2456,12 +2512,9 @@ static void set_irq_status(int vid) { uint32_t i; - uint64_t idx; - for (i = 0; i < rte_vhost_get_queue_num(vid); i++) { - idx = i * VIRTIO_QNUM; - rte_vhost_enable_guest_notification(vid, idx + VIRTIO_RXQ, 0); - rte_vhost_enable_guest_notification(vid, idx + VIRTIO_TXQ, 0); + for (i = 0; i < rte_vhost_get_vring_num(vid); i++) { + rte_vhost_enable_guest_notification(vid, i, 0); } } @@ -2524,7 +2577,7 @@ new_device(int vid) 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); @@ -2691,27 +2744,6 @@ netdev_dpdk_get_ingress_policer(const struct netdev_dpdk *dev) return ovsrcu_get(struct ingress_policer *, &dev->ingress_policer); } -/* - * These callbacks allow virtio-net devices to be added to vhost ports when - * configuration has been fully complete. - */ -static const struct virtio_net_device_ops virtio_net_device_ops = -{ - .new_device = new_device, - .destroy_device = destroy_device, - .vring_state_changed = vring_state_changed -}; - -static void * -start_vhost_loop(void *dummy OVS_UNUSED) -{ - pthread_detach(pthread_self()); - /* Put the vhost thread into quiescent state. */ - ovsrcu_quiesce_start(); - rte_vhost_driver_session_start(); - return NULL; -} - static int netdev_dpdk_class_init(void) { @@ -2731,25 +2763,6 @@ netdev_dpdk_class_init(void) return 0; } -static int -netdev_dpdk_vhost_class_init(void) -{ - static struct ovsthread_once once = OVSTHREAD_ONCE_INITIALIZER; - - /* This function can be called for different classes. The initialization - * needs to be done only once */ - if (ovsthread_once_start(&once)) { - rte_vhost_driver_callback_register(&virtio_net_device_ops); - rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4 - | 1ULL << VIRTIO_NET_F_HOST_TSO6 - | 1ULL << VIRTIO_NET_F_CSUM); - ovs_thread_create("vhost_thread", start_vhost_loop, NULL); - - ovsthread_once_done(&once); - } - - return 0; -} /* Client Rings */ @@ -3204,6 +3217,31 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev) "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); @@ -3324,7 +3362,7 @@ static const struct netdev_class dpdk_ring_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, @@ -3339,7 +3377,7 @@ static const struct netdev_class dpdk_vhost_class = 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, diff --git a/rhel/openvswitch-fedora.spec.in b/rhel/openvswitch-fedora.spec.in index 3a045d3..2bb7102 100644 --- a/rhel/openvswitch-fedora.spec.in +++ b/rhel/openvswitch-fedora.spec.in @@ -84,7 +84,7 @@ BuildRequires: libcap-ng libcap-ng-devel %endif %if %{with dpdk} BuildRequires: libpcap-devel numactl-devel -BuildRequires: dpdk-devel >= 16.11 +BuildRequires: dpdk-devel >= 17.05.1 Provides: %{name}-dpdk = %{version}-%{release} %endif diff --git a/tests/dpdk/ring_client.c b/tests/dpdk/ring_client.c index b153713..8cc3fb5 100644 --- a/tests/dpdk/ring_client.c +++ b/tests/dpdk/ring_client.c @@ -185,15 +185,15 @@ main(int argc, char *argv[]) /* Try dequeuing max possible packets first, if that fails, get the * most we can. Loop body should only execute once, maximum. */ - while (unlikely(rte_ring_dequeue_bulk(rx_ring, pkts, rx_pkts) != 0) && - rx_pkts > 0) { + while (unlikely(rte_ring_dequeue_bulk(rx_ring, pkts, + rx_pkts, NULL) != 0) && rx_pkts > 0) { rx_pkts = (uint16_t)RTE_MIN(rte_ring_count(rx_ring), PKT_READ_SIZE); } if (rx_pkts > 0) { /* blocking enqueue */ do { - rslt = rte_ring_enqueue_bulk(tx_ring, pkts, rx_pkts); + rslt = rte_ring_enqueue_bulk(tx_ring, pkts, rx_pkts, NULL); } while (rslt == -ENOBUFS); } } -- 1.8.3.1 _______________________________________________ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev