From patchwork Thu Apr 16 03:55:49 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jijiang Liu X-Patchwork-Id: 4320 Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id D967DC380; Thu, 16 Apr 2015 05:56:11 +0200 (CEST) Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 0B177C37C for ; Thu, 16 Apr 2015 05:56:09 +0200 (CEST) Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga102.fm.intel.com with ESMTP; 15 Apr 2015 20:56:08 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,585,1422950400"; d="scan'208";a="696060354" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by fmsmga001.fm.intel.com with ESMTP; 15 Apr 2015 20:56:08 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id t3G3u5R1005185; Thu, 16 Apr 2015 11:56:05 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id t3G3u18d028782; Thu, 16 Apr 2015 11:56:03 +0800 Received: (from jijiangl@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id t3G3u1mb028778; Thu, 16 Apr 2015 11:56:01 +0800 From: Jijiang Liu To: dev@dpdk.org, walter.e.gilmore@intel.com, thomas.long@intel.com Date: Thu, 16 Apr 2015 11:55:49 +0800 Message-Id: <1429156558-28548-2-git-send-email-jijiang.liu@intel.com> X-Mailer: git-send-email 1.7.12.2 In-Reply-To: <1429156558-28548-1-git-send-email-jijiang.liu@intel.com> References: <1429156558-28548-1-git-send-email-jijiang.liu@intel.com> Subject: [dpdk-dev] [PATCH RFC 01/10] examples/tep_termination:initialize the VXLAN example X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" This example uses the basic virtio devices management function from the vHost example, which includes virtio device creation, destroying and maintenance. Signed-off-by: Jijiang Liu --- examples/Makefile | 1 + examples/tep_termination/Makefile | 58 +++ examples/tep_termination/main.c | 998 +++++++++++++++++++++++++++++++++++++ examples/tep_termination/main.h | 113 +++++ 4 files changed, 1170 insertions(+), 0 deletions(-) create mode 100644 examples/tep_termination/Makefile create mode 100644 examples/tep_termination/main.c create mode 100644 examples/tep_termination/main.h diff --git a/examples/Makefile b/examples/Makefile index d549026..3f08954 100644 --- a/examples/Makefile +++ b/examples/Makefile @@ -73,5 +73,6 @@ DIRS-$(CONFIG_RTE_LIBRTE_XEN_DOM0) += vhost_xen DIRS-y += vmdq DIRS-y += vmdq_dcb DIRS-y += vm_power_manager +DIRS-y += tep_termination include $(RTE_SDK)/mk/rte.extsubdir.mk diff --git a/examples/tep_termination/Makefile b/examples/tep_termination/Makefile new file mode 100644 index 0000000..23fb647 --- /dev/null +++ b/examples/tep_termination/Makefile @@ -0,0 +1,58 @@ +# BSD LICENSE +# +# Copyright(c) 2010-2014 Intel Corporation. All rights reserved. +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# +# * Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in +# the documentation and/or other materials provided with the +# distribution. +# * Neither the name of Intel Corporation nor the names of its +# contributors may be used to endorse or promote products derived +# from this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, can be overriden by command line or environment +RTE_TARGET ?= x86_64-native-linuxapp-gcc + +include $(RTE_SDK)/mk/rte.vars.mk + +ifneq ($(CONFIG_RTE_EXEC_ENV),"linuxapp") +$(info This application can only operate in a linuxapp environment, \ +please change the definition of the RTE_TARGET environment variable) +all: +else + +# binary name +APP = tep_termination + +# all source are stored in SRCS-y +SRCS-y := main.c + +CFLAGS += -O2 -D_FILE_OFFSET_BITS=64 +CFLAGS += $(WERROR_FLAGS) + +include $(RTE_SDK)/mk/rte.extapp.mk + +endif diff --git a/examples/tep_termination/main.c b/examples/tep_termination/main.c new file mode 100644 index 0000000..2e36ad0 --- /dev/null +++ b/examples/tep_termination/main.c @@ -0,0 +1,998 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2015 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include "main.h" + +/* the maximum number of external ports supported */ +#define MAX_SUP_PORTS 1 + +/* + * Calculate the number of buffers needed per port + */ +#define NUM_MBUFS_PER_PORT ((MAX_QUEUES*RTE_TEST_RX_DESC_DEFAULT) + \ + (num_switching_cores*MAX_PKT_BURST) + \ + (num_switching_cores*RTE_TEST_TX_DESC_DEFAULT) +\ + (num_switching_cores*MBUF_CACHE_SIZE)) + +#define MBUF_CACHE_SIZE 128 +#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) + +#define MAX_PKT_BURST 32 /* Max burst size for RX/TX */ +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +#define BURST_RX_RETRIES 4/* Number of retries on RX. */ + +#define JUMBO_FRAME_MAX_SIZE 0x2600 + +/* Config_core_flag status definitions. */ +#define REQUEST_DEV_REMOVAL 1 +#define ACK_DEV_REMOVAL 0 + +#define INVALID_PORT_ID 0xFF + +/* Max number of virtIO device */ +#define MAX_DEVICES 64 + +/* Maximum character device basename size. */ +#define MAX_BASENAME_SZ 10 + +/* Maximum long option length for option parsing. */ +#define MAX_LONG_OPT_SZ 64 + +/* ethernet addresses of ports */ +struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; + +uint8_t ports[RTE_MAX_ETHPORTS]; + +static unsigned lcore_ids[RTE_MAX_LCORE]; + +/* mask of enabled ports */ +static uint32_t enabled_port_mask = 0; + +/*Number of switching cores enabled*/ +static uint32_t num_switching_cores = 0; + +struct vpool { + struct rte_mempool *pool; + struct rte_ring *ring; + uint32_t buf_size; +} vpool_array[MAX_QUEUES+MAX_QUEUES]; + +/* number of devices */ +uint16_t num_devices; + +/* Enable stats. */ +static uint32_t enable_stats = 0; + +/* Character device basename. Can be set by user. */ +static char dev_basename[MAX_BASENAME_SZ] = "vhost-net"; + +static unsigned num_ports = 0; /**< The number of ports specified in command line */ + +/* heads for the main used and free linked lists for the data path. */ +struct virtio_net_data_ll *ll_root_used = NULL; +struct virtio_net_data_ll *ll_root_free = NULL; + +/** + * Array of data core structures containing information + * on individual core linked lists. + */ +static struct lcore_info lcore_info[RTE_MAX_LCORE]; + +/* Used for queueing bursts of TX packets. */ +struct mbuf_table { + unsigned len; + unsigned txq_id; + struct rte_mbuf *m_table[MAX_PKT_BURST]; +}; + +/* TX queue for each data core. */ +struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE]; + +/* Per-device statistics struct */ +struct device_statistics { + uint64_t tx_total; + rte_atomic64_t rx_total_atomic; + uint64_t rx_total; + uint64_t tx; + rte_atomic64_t rx_atomic; + uint64_t rx; +} __rte_cache_aligned; + +struct device_statistics dev_statistics[MAX_DEVICES]; + +/* + * Set character device basename. + */ +static int +tep_parse_basename(const char *q_arg) +{ + /* parse number string */ + + if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ) + return -1; + else + snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg); + + return 0; +} + +/* + * Parse the portmask provided at run time. + */ +static int +parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + errno = 0; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0') || (errno != 0)) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +/* + * Parse num options at run time. + */ +static int +parse_num_opt(const char *q_arg, uint32_t max_valid_value) +{ + char *end = NULL; + unsigned long num; + + errno = 0; + + /* parse unsigned int string */ + num = strtoul(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0') || (errno != 0)) + return -1; + + if (num > max_valid_value) + return -1; + + return num; + +} + +/* + * Display usage + */ +static void +vep_termination_usage(const char *prgname) +{ + RTE_LOG(INFO, VHOST_CONFIG, "%s [EAL options] -- -p PORTMASK\n" + " --nb-devices: number of virtIO device\n" + " --dev-basename \n" + " -p PORTMASK: Set mask for ports to be used by application\n" + " --stats [0-N]: 0: Disable stats, N: Time in seconds to print stats\n" + " --dev-basename: The basename to be used for the character device.\n", + prgname); +} + +/* + * Parse the arguments given in the command line of the application. + */ +static int +tep_parse_args(int argc, char **argv) +{ + int opt, ret; + int option_index; + unsigned i; + const char *prgname = argv[0]; + static struct option long_option[] = { + {"nb-devices", required_argument, NULL, 0}, + {"stats", required_argument, NULL, 0}, + {"dev-basename", required_argument, NULL, 0}, + {NULL, 0, 0, 0}, + }; + + /* Parse command line */ + while ((opt = getopt_long(argc, argv, "p:P", + long_option, &option_index)) != EOF) { + switch (opt) { + /* Portmask */ + case 'p': + enabled_port_mask = parse_portmask(optarg); + if (enabled_port_mask == 0) { + RTE_LOG(INFO, VHOST_CONFIG, "Invalid portmask\n"); + vep_termination_usage(prgname); + return -1; + } + break; + + case 0: + if (!strncmp(long_option[option_index].name, "nb-devices", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, MAX_DEVICES); + if (ret == -1) { + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for nb-devices [0-%d]\n", MAX_DEVICES); + vep_termination_usage(prgname); + return -1; + } else + num_devices = ret; + } + + /* Enable/disable stats. */ + if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, INT32_MAX); + if (ret == -1) { + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for stats [0..N]\n"); + vep_termination_usage(prgname); + return -1; + } else + enable_stats = ret; + } + + /* Set character device basename. */ + if (!strncmp(long_option[option_index].name, "dev-basename", MAX_LONG_OPT_SZ)) { + if (tep_parse_basename(optarg) == -1) { + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device " + "basename (Max %d characters)\n", MAX_BASENAME_SZ); + vep_termination_usage(prgname); + return -1; + } + } + + break; + + /* Invalid option - print options. */ + default: + vep_termination_usage(prgname); + return -1; + } + } + + for (i = 0; i < RTE_MAX_ETHPORTS; i++) { + if (enabled_port_mask & (1 << i)) + ports[num_ports++] = (uint8_t)i; + } + + if ((num_ports == 0) || (num_ports > MAX_SUP_PORTS)) { + RTE_LOG(INFO, VHOST_PORT, "Current enabled port number is %u," + "but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS); + return -1; + } + + return 0; +} + +/* + * Update the global var NUM_PORTS and array PORTS according to system ports number + * and return valid ports number + */ +static unsigned check_ports_num(unsigned nb_ports) +{ + unsigned valid_num_ports = num_ports; + unsigned portid; + + if (num_ports > nb_ports) { + RTE_LOG(INFO, VHOST_PORT, "\nSpecified port number(%u) exceeds total system port number(%u)\n", + num_ports, nb_ports); + num_ports = nb_ports; + } + + for (portid = 0; portid < num_ports; portid ++) { + if (ports[portid] >= nb_ports) { + RTE_LOG(INFO, VHOST_PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n", + ports[portid], (nb_ports - 1)); + ports[portid] = INVALID_PORT_ID; + valid_num_ports--; + } + } + return valid_num_ports; +} + +/* + * This function routes the TX packet to the correct interface. This may be a local device + * or the physical port. + */ +static inline void __attribute__((always_inline)) +virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, __attribute__((unused)) uint16_t vlan_tag) +{ + struct mbuf_table *tx_q; + struct rte_mbuf **m_table; + unsigned len, ret = 0; + + const uint16_t lcore_id = rte_lcore_id(); + struct virtio_net *dev = vdev->dev; + + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh); + + /*Add packet to the port tx queue*/ + tx_q = &lcore_tx_queue[lcore_id]; + len = tx_q->len; + tx_q->m_table[len] = m; + len++; + if (enable_stats) { + dev_statistics[dev->device_fh].tx_total++; + dev_statistics[dev->device_fh].tx++; + } + + if (unlikely(len == MAX_PKT_BURST)) { + m_table = (struct rte_mbuf **)tx_q->m_table; + /* Free any buffers not handled by TX and update the port stats. */ + if (unlikely(ret < len)) { + do { + rte_pktmbuf_free(m_table[ret]); + } while (++ret < len); + } + + len = 0; + } + + tx_q->len = len; + return; +} + +/* + * This function is called by each data core. It handles all RX/TX registered with the + * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared + * with all devices in the main linked list. + */ +static int +switch_worker(__attribute__((unused)) void *arg) +{ + struct rte_mempool *mbuf_pool = arg; + struct virtio_net *dev = NULL; + struct vhost_dev *vdev = NULL; + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *mbuf_tmp = NULL; + struct virtio_net_data_ll *dev_ll; + struct mbuf_table *tx_q; + volatile struct lcore_ll_info *lcore_ll; + const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US; + uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0; + unsigned ret = 0, i; + const uint16_t lcore_id = rte_lcore_id(); + const uint16_t num_cores = (uint16_t)rte_lcore_count(); + uint16_t rx_count = 0; + uint16_t tx_count; + + RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id); + lcore_ll = lcore_info[lcore_id].lcore_ll; + prev_tsc = 0; + + tx_q = &lcore_tx_queue[lcore_id]; + for (i = 0; i < num_cores; i ++) { + if (lcore_ids[i] == lcore_id) { + tx_q->txq_id = i; + break; + } + } + + while(1) { + cur_tsc = rte_rdtsc(); + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + + if (tx_q->len) { + LOG_DEBUG(VHOST_DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len); + if (unlikely(ret < tx_q->len)) { + do { + rte_pktmbuf_free(tx_q->m_table[ret]); + } while (++ret < tx_q->len); + } + + tx_q->len = 0; + } + + prev_tsc = cur_tsc; + + } + + rte_prefetch0(lcore_ll->ll_root_used); + /* + * Inform the configuration core that we have exited the linked list and that no devices are + * in use if requested. + */ + if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL) + lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL; + + /* + * Process devices + */ + dev_ll = lcore_ll->ll_root_used; + + while (dev_ll != NULL) { + /*get virtio device ID*/ + vdev = dev_ll->vdev; + dev = vdev->dev; + + if (unlikely(vdev->remove)) { + dev_ll = dev_ll->next; + vdev->ready = DEVICE_SAFE_REMOVE; + continue; + } + + if (likely(vdev->ready == DEVICE_RX)) { + /*Handle guest RX*/ + rx_count = rte_eth_rx_burst(ports[0], + vdev->rx_q, pkts_burst, MAX_PKT_BURST); + + if (rx_count) { + if (enable_stats) { + rte_atomic64_add( + &dev_statistics[dev_ll->vdev->dev->device_fh].rx_total_atomic, + rx_count); + rte_atomic64_add( + &dev_statistics[dev_ll->vdev->dev->device_fh].rx_atomic, ret_count); + } + while (likely(rx_count)) { + rx_count--; + rte_pktmbuf_free(pkts_burst[rx_count]); + } + + } + } + + if (likely(!vdev->remove)) { + /* Handle guest TX*/ + tx_count = rte_vhost_dequeue_burst(dev, VIRTIO_TXQ, mbuf_pool, pkts_burst, MAX_PKT_BURST); + /* If this is the first received packet we need to learn the MAC */ + if (unlikely(vdev->ready == DEVICE_MAC_LEARNING) && tx_count) { + if (vdev->remove) { + while (tx_count) { + mbuf_tmp = pkts_burst[--tx_count]; + if (mbuf_tmp) + rte_pktmbuf_free(mbuf_tmp); + } + } + } + while (tx_count) { + mbuf_tmp = pkts_burst[--tx_count]; + if (mbuf_tmp) + virtio_tx_route(vdev, mbuf_tmp, (uint16_t)dev->device_fh); + } + } + + /*move to the next device in the list*/ + dev_ll = dev_ll->next; + } + } + + return 0; +} + +/* + * Add an entry to a used linked list. A free entry must first be found + * in the free linked list using get_data_ll_free_entry(); + */ +static void +add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, + struct virtio_net_data_ll *ll_dev) +{ + struct virtio_net_data_ll *ll = *ll_root_addr; + + /* Set next as NULL and use a compiler barrier to avoid reordering. */ + ll_dev->next = NULL; + rte_compiler_barrier(); + + /* If ll == NULL then this is the first device. */ + if (ll) { + /* Increment to the tail of the linked list. */ + while ((ll->next != NULL) ) + ll = ll->next; + + ll->next = ll_dev; + } else { + *ll_root_addr = ll_dev; + } +} + +/* + * Remove an entry from a used linked list. The entry must then be added to + * the free linked list using put_data_ll_free_entry(). + */ +static void +rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, + struct virtio_net_data_ll *ll_dev, + struct virtio_net_data_ll *ll_dev_last) +{ + struct virtio_net_data_ll *ll = *ll_root_addr; + + if (unlikely((ll == NULL) || (ll_dev == NULL))) + return; + + if (ll_dev == ll) + *ll_root_addr = ll_dev->next; + else + if (likely(ll_dev_last != NULL)) + ll_dev_last->next = ll_dev->next; + else + RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n"); +} + +/* + * Find and return an entry from the free linked list. + */ +static struct virtio_net_data_ll * +get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr) +{ + struct virtio_net_data_ll *ll_free = *ll_root_addr; + struct virtio_net_data_ll *ll_dev; + + if (ll_free == NULL) + return NULL; + + ll_dev = ll_free; + *ll_root_addr = ll_free->next; + + return ll_dev; +} + +/* + * Place an entry back on to the free linked list. + */ +static void +put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr, + struct virtio_net_data_ll *ll_dev) +{ + struct virtio_net_data_ll *ll_free = *ll_root_addr; + + if (ll_dev == NULL) + return; + + ll_dev->next = ll_free; + *ll_root_addr = ll_dev; +} + +/* + * Creates a linked list of a given size. + */ +static struct virtio_net_data_ll * +alloc_data_ll(uint32_t size) +{ + struct virtio_net_data_ll *ll_new; + uint32_t i; + + /* Malloc and then chain the linked list. */ + ll_new = malloc(size * sizeof(struct virtio_net_data_ll)); + if (ll_new == NULL) { + RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for ll_new.\n"); + return NULL; + } + + for (i = 0; i < size - 1; i++) { + ll_new[i].vdev = NULL; + ll_new[i].next = &ll_new[i+1]; + } + ll_new[i].next = NULL; + + return (ll_new); +} + +/* + * Create the main linked list along with each individual cores linked list. A used and a free list + * are created to manage entries. + */ +static int +init_data_ll (void) +{ + int lcore; + + RTE_LCORE_FOREACH_SLAVE(lcore) { + lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info)); + if (lcore_info[lcore].lcore_ll == NULL) { + RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n"); + return -1; + } + + lcore_info[lcore].lcore_ll->device_num = 0; + lcore_info[lcore].lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL; + lcore_info[lcore].lcore_ll->ll_root_used = NULL; + if (num_devices % num_switching_cores) + lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll((num_devices / num_switching_cores) + 1); + else + lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll(num_devices / num_switching_cores); + } + + /* Allocate devices up to a maximum of MAX_DEVICES. */ + ll_root_free = alloc_data_ll(MIN((num_devices), MAX_DEVICES)); + + return 0; +} + +/* + * Remove a device from the specific data core linked list and from the main linked list. Synchonization + * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering + * of dev->remove=1 which can cause an infinite loop in the rte_pause loop. + */ +static void +destroy_device (volatile struct virtio_net *dev) +{ + struct virtio_net_data_ll *ll_lcore_dev_cur; + struct virtio_net_data_ll *ll_main_dev_cur; + struct virtio_net_data_ll *ll_lcore_dev_last = NULL; + struct virtio_net_data_ll *ll_main_dev_last = NULL; + struct vhost_dev *vdev; + int lcore; + + dev->flags &= ~VIRTIO_DEV_RUNNING; + + vdev = (struct vhost_dev *)dev->priv; + /*set the remove flag. */ + vdev->remove = 1; + while(vdev->ready != DEVICE_SAFE_REMOVE) { + rte_pause(); + } + + /* Search for entry to be removed from lcore ll */ + ll_lcore_dev_cur = lcore_info[vdev->coreid].lcore_ll->ll_root_used; + while (ll_lcore_dev_cur != NULL) { + if (ll_lcore_dev_cur->vdev == vdev) { + break; + } else { + ll_lcore_dev_last = ll_lcore_dev_cur; + ll_lcore_dev_cur = ll_lcore_dev_cur->next; + } + } + + if (ll_lcore_dev_cur == NULL) { + RTE_LOG(ERR, VHOST_CONFIG, + "(%"PRIu64") Failed to find the dev to be destroy.\n", + dev->device_fh); + return; + } + + /* Search for entry to be removed from main ll */ + ll_main_dev_cur = ll_root_used; + ll_main_dev_last = NULL; + while (ll_main_dev_cur != NULL) { + if (ll_main_dev_cur->vdev == vdev) { + break; + } else { + ll_main_dev_last = ll_main_dev_cur; + ll_main_dev_cur = ll_main_dev_cur->next; + } + } + + /* Remove entries from the lcore and main ll. */ + rm_data_ll_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_used, ll_lcore_dev_cur, ll_lcore_dev_last); + rm_data_ll_entry(&ll_root_used, ll_main_dev_cur, ll_main_dev_last); + + /* Set the dev_removal_flag on each lcore. */ + RTE_LCORE_FOREACH_SLAVE(lcore) { + lcore_info[lcore].lcore_ll->dev_removal_flag = REQUEST_DEV_REMOVAL; + } + + /* + * Once each core has set the dev_removal_flag to ACK_DEV_REMOVAL we can be sure that + * they can no longer access the device removed from the linked lists and that the devices + * are no longer in use. + */ + RTE_LCORE_FOREACH_SLAVE(lcore) { + while (lcore_info[lcore].lcore_ll->dev_removal_flag != ACK_DEV_REMOVAL) { + rte_pause(); + } + } + + /* Add the entries back to the lcore and main free ll.*/ + put_data_ll_free_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur); + put_data_ll_free_entry(&ll_root_free, ll_main_dev_cur); + + /* Decrement number of device on the lcore. */ + lcore_info[vdev->coreid].lcore_ll->device_num--; + + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh); + + rte_free(vdev); + +} + +/* + * A new device is added to a data core. First the device is added to the main linked list + * and the allocated to a specific data core. + */ +static int +new_device (struct virtio_net *dev) +{ + struct virtio_net_data_ll *ll_dev; + int lcore, core_add = 0; + uint32_t device_num_min = num_devices; + struct vhost_dev *vdev; + + vdev = rte_zmalloc("vhost device", sizeof(*vdev), RTE_CACHE_LINE_SIZE); + if (vdev == NULL) { + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Couldn't allocate memory for vhost dev\n", + dev->device_fh); + return -1; + } + vdev->dev = dev; + dev->priv = vdev; + + /* Add device to main ll */ + ll_dev = get_data_ll_free_entry(&ll_root_free); + if (ll_dev == NULL) { + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") No free entry found in linked list. Device limit " + "of %d devices per core has been reached\n", + dev->device_fh, num_devices); + if (vdev->regions_hpa) + rte_free(vdev->regions_hpa); + rte_free(vdev); + return -1; + } + ll_dev->vdev = vdev; + add_data_ll_entry(&ll_root_used, ll_dev); + vdev->rx_q = dev->device_fh; + + /*reset ready flag*/ + vdev->ready = DEVICE_MAC_LEARNING; + vdev->remove = 0; + + /* Find a suitable lcore to add the device. */ + RTE_LCORE_FOREACH_SLAVE(lcore) { + if (lcore_info[lcore].lcore_ll->device_num < device_num_min) { + device_num_min = lcore_info[lcore].lcore_ll->device_num; + core_add = lcore; + } + } + /* Add device to lcore ll */ + ll_dev = get_data_ll_free_entry(&lcore_info[core_add].lcore_ll->ll_root_free); + if (ll_dev == NULL) { + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh); + vdev->ready = DEVICE_SAFE_REMOVE; + destroy_device(dev); + if (vdev->regions_hpa) + rte_free(vdev->regions_hpa); + rte_free(vdev); + return -1; + } + ll_dev->vdev = vdev; + vdev->coreid = core_add; + + add_data_ll_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_used, ll_dev); + + /* Initialize device stats */ + memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics)); + + /* Disable notifications. */ + rte_vhost_enable_guest_notification(dev, VIRTIO_RXQ, 0); + rte_vhost_enable_guest_notification(dev, VIRTIO_TXQ, 0); + lcore_info[vdev->coreid].lcore_ll->device_num++; + dev->flags |= VIRTIO_DEV_RUNNING; + + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, vdev->coreid); + + return 0; +} + +/* + * These callback allow devices to be added to the data core 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, +}; + +/* + * This is a thread will wake up after a period to print stats if the user has + * enabled them. + */ +static void +print_stats(void) +{ + struct virtio_net_data_ll *dev_ll; + uint64_t tx_dropped, rx_dropped; + uint64_t tx, tx_total, rx, rx_total; + uint32_t device_fh; + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char top_left[] = { 27, '[', '1', ';', '1', 'H','\0' }; + + while(1) { + sleep(enable_stats); + + /* Clear screen and move to top left */ + printf("%s%s", clr, top_left); + + printf("\nDevice statistics ===================================="); + + dev_ll = ll_root_used; + while (dev_ll != NULL) { + device_fh = (uint32_t)dev_ll->vdev->dev->device_fh; + tx_total = dev_statistics[device_fh].tx_total; + tx = dev_statistics[device_fh].tx; + tx_dropped = tx_total - tx; + rx_total = rte_atomic64_read( + &dev_statistics[device_fh].rx_total_atomic); + rx = rte_atomic64_read( + &dev_statistics[device_fh].rx_atomic); + rx_dropped = rx_total - rx; + + printf("\nStatistics for device %"PRIu32" ------------------------------" + "\nTX total: %"PRIu64"" + "\nTX dropped: %"PRIu64"" + "\nTX successful: %"PRIu64"" + "\nRX total: %"PRIu64"" + "\nRX dropped: %"PRIu64"" + "\nRX successful: %"PRIu64"", + device_fh, + tx_total, + tx_dropped, + tx, + rx_total, + rx_dropped, + rx); + + dev_ll = dev_ll->next; + } + printf("\n======================================================\n"); + } +} + +/* + * Main function, does initialisation and calls the per-lcore functions. The CUSE + * device is also registered here to handle the IOCTLs. + */ +int +main(int argc, char *argv[]) +{ + struct rte_mempool *mbuf_pool = NULL; + unsigned lcore_id, core_id = 0; + unsigned nb_ports, valid_num_ports; + int ret; + uint8_t portid; + uint16_t queue_id; + static pthread_t tid; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Error with EAL initialization\n"); + argc -= ret; + argv += ret; + + /* parse app arguments */ + ret = tep_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid argument\n"); + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++) + if (rte_lcore_is_enabled(lcore_id)) + lcore_ids[core_id ++] = lcore_id; + + if (rte_lcore_count() > RTE_MAX_LCORE) + rte_exit(EXIT_FAILURE,"Not enough cores\n"); + + /*set the number of swithcing cores available*/ + num_switching_cores = rte_lcore_count()-1; + + /* Get the number of physical ports. */ + nb_ports = rte_eth_dev_count(); + if (nb_ports > RTE_MAX_ETHPORTS) + nb_ports = RTE_MAX_ETHPORTS; + + + /* + * Update the global var NUM_PORTS and global array PORTS + * and get value of var VALID_NUM_PORTS according to system ports number + */ + valid_num_ports = check_ports_num(nb_ports); + + if ((valid_num_ports == 0) || (valid_num_ports > MAX_SUP_PORTS)) { + RTE_LOG(INFO, VHOST_PORT, "Current enabled port number is %u," + "but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS); + return -1; + } + + + /* Create the mbuf pool. */ + mbuf_pool = rte_mempool_create( + "MBUF_POOL", + NUM_MBUFS_PER_PORT + * valid_num_ports, + MBUF_SIZE, MBUF_CACHE_SIZE, + sizeof(struct rte_pktmbuf_pool_private), + rte_pktmbuf_pool_init, NULL, + rte_pktmbuf_init, NULL, + rte_socket_id(), 0); + if (mbuf_pool == NULL) + rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n"); + + for (queue_id = 0; queue_id < MAX_QUEUES + 1; queue_id++) + vpool_array[queue_id].pool = mbuf_pool; + + /* Set log level. */ + rte_set_log_level(LOG_LEVEL); + + /* initialize all ports */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((enabled_port_mask & (1 << portid)) == 0) { + RTE_LOG(INFO, VHOST_PORT, + "Skipping disabled port %d\n", portid); + continue; + } + } + + /* Initialise all linked lists. */ + if (init_data_ll() == -1) + rte_exit(EXIT_FAILURE, "Failed to initialize linked list\n"); + + /* Initialize device stats */ + memset(&dev_statistics, 0, sizeof(dev_statistics)); + + /* Enable stats if the user option is set. */ + if (enable_stats) + pthread_create(&tid, NULL, (void*)print_stats, NULL ); + + /* Launch all data cores. */ + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + rte_eal_remote_launch(switch_worker, + mbuf_pool, lcore_id); + } + + rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF); + + /* Register CUSE device to handle IOCTLs. */ + ret = rte_vhost_driver_register((char *)&dev_basename); + if (ret != 0) + rte_exit(EXIT_FAILURE,"CUSE device setup failure.\n"); + + rte_vhost_driver_callback_register(&virtio_net_device_ops); + + /* Start CUSE session. */ + rte_vhost_driver_session_start(); + return 0; +} diff --git a/examples/tep_termination/main.h b/examples/tep_termination/main.h new file mode 100644 index 0000000..8fb4d5d --- /dev/null +++ b/examples/tep_termination/main.h @@ -0,0 +1,113 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2015 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MAIN_H_ +#define _MAIN_H_ + +#ifdef DEBUG +#define LOG_LEVEL RTE_LOG_DEBUG +#define LOG_DEBUG(log_type, fmt, args...) do { \ + RTE_LOG(DEBUG, log_type, fmt, ##args); \ +} while (0) +#else +#define LOG_LEVEL RTE_LOG_INFO +#define LOG_DEBUG(log_type, fmt, args...) do{} while(0) +#endif + +/* Macros for printing using RTE_LOG */ +#define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1 +#define RTE_LOGTYPE_VHOST_DATA RTE_LOGTYPE_USER2 +#define RTE_LOGTYPE_VHOST_PORT RTE_LOGTYPE_USER3 + +/* State of virtio device. */ +#define DEVICE_MAC_LEARNING 0 +#define DEVICE_RX 1 +#define DEVICE_SAFE_REMOVE 2 + +#define MAX_QUEUES 512 + +/* Max burst size for RX/TX */ +#define MAX_PKT_BURST 32 + +/* Configurable number of RX/TX ring descriptors */ +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 512 + +/* * + * Device linked list structure for data path. + */ +struct vhost_dev { + /**< Pointer to device created by vhost lib. */ + struct virtio_net *dev; + /**< Number of memory regions for gpa to hpa translation. */ + uint32_t nregions_hpa; + /**< Memory region information for gpa to hpa translation. */ + struct virtio_memory_regions_hpa *regions_hpa; + /**< Device MAC address (Obtained on first TX packet). */ + struct ether_addr mac_address; + /**< RX queue number. */ + uint16_t rx_q; + /**< Data core that the device is added to. */ + uint16_t coreid; + /**< A device is set as ready if the MAC address has been set. */ + volatile uint8_t ready; + /**< Device is marked for removal from the data core. */ + volatile uint8_t remove; +} __rte_cache_aligned; + +/* * + * Structure containing data core specific information. + */ +struct lcore_ll_info +{ + struct virtio_net_data_ll *ll_root_free; /* Pointer to head in free linked list. */ + struct virtio_net_data_ll *ll_root_used; /* Pointer to head of used linked list. */ + uint32_t device_num; /* Number of devices on lcore. */ + volatile uint8_t dev_removal_flag; /* Flag to synchronize device removal. */ +}; + +struct lcore_info +{ + struct lcore_ll_info *lcore_ll; /* Pointer to data core specific lcore_ll_info struct */ +}; + +struct virtio_net_data_ll +{ + struct vhost_dev *vdev; /* Pointer to device created by configuration core. */ + struct virtio_net_data_ll *next; /* Pointer to next device in linked list. */ +}; + +uint32_t +virtio_dev_rx(struct virtio_net *dev, struct rte_mbuf **pkts, uint32_t count); + +#endif /* _MAIN_H_ */