X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fvhost%2Fmain.c;h=22d6a4b92aaa8367a6003dfc66808afd1203dc07;hb=ea0c20ea95fd5d71a10757e6598ac66233ea1495;hp=816a71a9202e9fb4437e8195685093531625a419;hpb=4796ad63ba1f05de5a3c15d00339aea3b73931ae;p=dpdk.git diff --git a/examples/vhost/main.c b/examples/vhost/main.c index 816a71a920..22d6a4b92a 100644 --- a/examples/vhost/main.c +++ b/examples/vhost/main.c @@ -1,13 +1,13 @@ /*- * 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 @@ -17,7 +17,7 @@ * * 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 @@ -48,12 +48,12 @@ #include #include #include +#include +#include #include "main.h" -#include "virtio-net.h" -#include "vhost-net-cdev.h" -#define MAX_QUEUES 128 +#define MAX_QUEUES 512 /* the maximum number of external ports supported */ #define MAX_SUP_PORTS 1 @@ -66,35 +66,26 @@ (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 MBUF_CACHE_SIZE 128 +#define MBUF_DATA_SIZE (2048 + RTE_PKTMBUF_HEADROOM) /* - * RX and TX Prefetch, Host, and Write-back threshold values should be - * carefully set for optimal performance. Consult the network - * controller's datasheet and supporting DPDK documentation for guidance - * on how these parameters should be set. + * No frame data buffer allocated from host are required for zero copy + * implementation, guest will allocate the frame data buffer, and vhost + * directly use it. */ -#define RX_PTHRESH 8 /* Default values of RX prefetch threshold reg. */ -#define RX_HTHRESH 8 /* Default values of RX host threshold reg. */ -#define RX_WTHRESH 4 /* Default values of RX write-back threshold reg. */ - -/* - * These default values are optimized for use with the Intel(R) 82599 10 GbE - * Controller and the DPDK ixgbe PMD. Consider using other values for other - * network controllers and/or network drivers. - */ -#define TX_PTHRESH 36 /* Default values of TX prefetch threshold reg. */ -#define TX_HTHRESH 0 /* Default values of TX host threshold reg. */ -#define TX_WTHRESH 0 /* Default values of TX write-back threshold reg. */ +#define VIRTIO_DESCRIPTOR_LEN_ZCP 1518 +#define MBUF_DATA_SIZE_ZCP (VIRTIO_DESCRIPTOR_LEN_ZCP + RTE_PKTMBUF_HEADROOM) +#define MBUF_CACHE_SIZE_ZCP 0 #define MAX_PKT_BURST 32 /* Max burst size for RX/TX */ -#define MAX_MRG_PKT_BURST 16 /* Max burst for merge buffers. Set to 1 due to performance issue. */ #define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ #define BURST_RX_WAIT_US 15 /* Defines how long we wait between retries on RX */ #define BURST_RX_RETRIES 4 /* Number of retries on RX. */ +#define JUMBO_FRAME_MAX_SIZE 0x2600 + /* State of virtio device. */ #define DEVICE_MAC_LEARNING 0 #define DEVICE_RX 1 @@ -105,15 +96,34 @@ #define ACK_DEV_REMOVAL 0 /* Configurable number of RX/TX ring descriptors */ -#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_RX_DESC_DEFAULT 1024 #define RTE_TEST_TX_DESC_DEFAULT 512 +/* + * Need refine these 2 macros for legacy and DPDK based front end: + * Max vring avail descriptor/entries from guest - MAX_PKT_BURST + * And then adjust power 2. + */ +/* + * For legacy front end, 128 descriptors, + * half for virtio header, another half for mbuf. + */ +#define RTE_TEST_RX_DESC_DEFAULT_ZCP 32 /* legacy: 32, DPDK virt FE: 128. */ +#define RTE_TEST_TX_DESC_DEFAULT_ZCP 64 /* legacy: 64, DPDK virt FE: 64. */ + +/* Get first 4 bytes in mbuf headroom. */ +#define MBUF_HEADROOM_UINT32(mbuf) (*(uint32_t *)((uint8_t *)(mbuf) \ + + sizeof(struct rte_mbuf))) + +/* true if x is a power of 2 */ +#define POWEROF2(x) ((((x)-1) & (x)) == 0) + #define INVALID_PORT_ID 0xFF /* Max number of devices. Limited by vmdq. */ #define MAX_DEVICES 64 -/* Size of buffers used for rte_snprintfs. */ +/* Size of buffers used for snprintfs. */ #define MAX_PRINT_BUFF 6072 /* Maximum character device basename size. */ @@ -126,20 +136,63 @@ #define MAC_ADDR_CMP 0xFFFFFFFFFFFFULL /* Number of descriptors per cacheline. */ -#define DESC_PER_CACHELINE (CACHE_LINE_SIZE / sizeof(struct vring_desc)) +#define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc)) + +#define MBUF_EXT_MEM(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb)) /* mask of enabled ports */ static uint32_t enabled_port_mask = 0; +/* Promiscuous mode */ +static uint32_t promiscuous; + /*Number of switching cores enabled*/ static uint32_t num_switching_cores = 0; /* number of devices/queues to support*/ static uint32_t num_queues = 0; -uint32_t num_devices = 0; +static uint32_t num_devices; + +/* + * Enable zero copy, pkts buffer will directly dma to hw descriptor, + * disabled on default. + */ +static uint32_t zero_copy; +static int mergeable; + +/* Do vlan strip on host, enabled on default */ +static uint32_t vlan_strip = 1; + +/* number of descriptors to apply*/ +static uint32_t num_rx_descriptor = RTE_TEST_RX_DESC_DEFAULT_ZCP; +static uint32_t num_tx_descriptor = RTE_TEST_TX_DESC_DEFAULT_ZCP; + +/* max ring descriptor, ixgbe, i40e, e1000 all are 4096. */ +#define MAX_RING_DESC 4096 + +struct vpool { + struct rte_mempool *pool; + struct rte_ring *ring; + uint32_t buf_size; +} vpool_array[MAX_QUEUES+MAX_QUEUES]; /* Enable VM2VM communications. If this is disabled then the MAC address compare is skipped. */ -static uint32_t enable_vm2vm = 1; +typedef enum { + VM2VM_DISABLED = 0, + VM2VM_SOFTWARE = 1, + VM2VM_HARDWARE = 2, + VM2VM_LAST +} vm2vm_type; +static vm2vm_type vm2vm_mode = VM2VM_SOFTWARE; + +/* The type of host physical address translated from guest physical address. */ +typedef enum { + PHYS_ADDR_CONTINUOUS = 0, + PHYS_ADDR_CROSS_SUBREG = 1, + PHYS_ADDR_INVALID = 2, + PHYS_ADDR_LAST +} hpa_type; + /* Enable stats. */ static uint32_t enable_stats = 0; /* Enable retries on RX. */ @@ -152,39 +205,8 @@ static uint32_t burst_rx_retry_num = BURST_RX_RETRIES; /* Character device basename. Can be set by user. */ static char dev_basename[MAX_BASENAME_SZ] = "vhost-net"; -/* Charater device index. Can be set by user. */ -static uint32_t dev_index = 0; - -/* This can be set by the user so it is made available here. */ -extern uint64_t VHOST_FEATURES; - -/* Default configuration for rx and tx thresholds etc. */ -static const struct rte_eth_rxconf rx_conf_default = { - .rx_thresh = { - .pthresh = RX_PTHRESH, - .hthresh = RX_HTHRESH, - .wthresh = RX_WTHRESH, - }, - .rx_drop_en = 1, -}; - -/* - * These default values are optimized for use with the Intel(R) 82599 10 GbE - * Controller and the DPDK ixgbe/igb PMD. Consider using other values for other - * network controllers and/or network drivers. - */ -static const struct rte_eth_txconf tx_conf_default = { - .tx_thresh = { - .pthresh = TX_PTHRESH, - .hthresh = TX_HTHRESH, - .wthresh = TX_WTHRESH, - }, - .tx_free_thresh = 0, /* Use PMD default values */ - .tx_rs_thresh = 0, /* Use PMD default values */ -}; - /* empty vmdq configuration structure. Filled in programatically */ -static const struct rte_eth_conf vmdq_conf_default = { +static struct rte_eth_conf vmdq_conf_default = { .rxmode = { .mq_mode = ETH_MQ_RX_VMDQ_ONLY, .split_hdr_size = 0, @@ -222,7 +244,11 @@ static const struct rte_eth_conf vmdq_conf_default = { static unsigned lcore_ids[RTE_MAX_LCORE]; static uint8_t ports[RTE_MAX_ETHPORTS]; static unsigned num_ports = 0; /**< The number of ports specified in command line */ +static uint16_t num_pf_queues, num_vmdq_queues; +static uint16_t vmdq_pool_base, vmdq_queue_base; +static uint16_t queues_per_pool; +static const uint16_t external_pkt_default_vlan_tag = 2000; const uint16_t vlan_tags[] = { 1000, 1001, 1002, 1003, 1004, 1005, 1006, 1007, 1008, 1009, 1010, 1011, 1012, 1013, 1014, 1015, @@ -254,6 +280,9 @@ struct mbuf_table { /* TX queue for each data core. */ struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE]; +/* TX queue fori each virtio device for zero copy. */ +struct mbuf_table tx_queue_zcp[MAX_QUEUES]; + /* Vlan header struct used to insert vlan tags on TX. */ struct vlan_ethhdr { unsigned char h_dest[ETH_ALEN]; @@ -263,6 +292,20 @@ struct vlan_ethhdr { __be16 h_vlan_encapsulated_proto; }; +/* IPv4 Header */ +struct ipv4_hdr { + uint8_t version_ihl; /**< version and header length */ + uint8_t type_of_service; /**< type of service */ + uint16_t total_length; /**< length of packet */ + uint16_t packet_id; /**< packet ID */ + uint16_t fragment_offset; /**< fragmentation offset */ + uint8_t time_to_live; /**< time to live */ + uint8_t next_proto_id; /**< protocol ID */ + uint16_t hdr_checksum; /**< header checksum */ + uint32_t src_addr; /**< source address */ + uint32_t dst_addr; /**< destination address */ +} __attribute__((__packed__)); + /* Header lengths. */ #define VLAN_HLEN 4 #define VLAN_ETH_HLEN 18 @@ -270,9 +313,11 @@ struct vlan_ethhdr { /* Per-device statistics struct */ struct device_statistics { uint64_t tx_total; - rte_atomic64_t rx_total; + rte_atomic64_t rx_total_atomic; + uint64_t rx_total; uint64_t tx; - rte_atomic64_t rx; + rte_atomic64_t rx_atomic; + uint64_t rx; } __rte_cache_aligned; struct device_statistics dev_statistics[MAX_DEVICES]; @@ -284,11 +329,15 @@ static inline int get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_devices) { struct rte_eth_vmdq_rx_conf conf; + struct rte_eth_vmdq_rx_conf *def_conf = + &vmdq_conf_default.rx_adv_conf.vmdq_rx_conf; unsigned i; memset(&conf, 0, sizeof(conf)); conf.nb_queue_pools = (enum rte_eth_nb_pools)num_devices; conf.nb_pool_maps = num_devices; + conf.enable_loop_back = def_conf->enable_loop_back; + conf.rx_mode = def_conf->rx_mode; for (i = 0; i < conf.nb_pool_maps; i++) { conf.pool_map[i].vlan_id = vlan_tags[ i ]; @@ -302,15 +351,15 @@ get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_devices) } /* - * Validate the device number according to the max pool number gotten form dev_info - * If the device number is invalid, give the error message and return -1. - * Each device must have its own pool. + * Validate the device number according to the max pool number gotten form + * dev_info. If the device number is invalid, give the error message and + * return -1. Each device must have its own pool. */ static inline int validate_num_devices(uint32_t max_nb_devices) { if (num_devices > max_nb_devices) { - RTE_LOG(ERR, PORT, "invalid number of devices\n"); + RTE_LOG(ERR, VHOST_PORT, "invalid number of devices\n"); return -1; } return 0; @@ -321,21 +370,56 @@ validate_num_devices(uint32_t max_nb_devices) * coming from the mbuf_pool passed as parameter */ static inline int -port_init(uint8_t port, struct rte_mempool *mbuf_pool) +port_init(uint8_t port) { struct rte_eth_dev_info dev_info; struct rte_eth_conf port_conf; - uint16_t rx_rings, tx_rings = (uint16_t)rte_lcore_count(); - const uint16_t rx_ring_size = RTE_TEST_RX_DESC_DEFAULT, tx_ring_size = RTE_TEST_TX_DESC_DEFAULT; + struct rte_eth_rxconf *rxconf; + struct rte_eth_txconf *txconf; + int16_t rx_rings, tx_rings; + uint16_t rx_ring_size, tx_ring_size; int retval; uint16_t q; /* The max pool number from dev_info will be used to validate the pool number specified in cmd line */ rte_eth_dev_info_get (port, &dev_info); + if (dev_info.max_rx_queues > MAX_QUEUES) { + rte_exit(EXIT_FAILURE, + "please define MAX_QUEUES no less than %u in %s\n", + dev_info.max_rx_queues, __FILE__); + } + + rxconf = &dev_info.default_rxconf; + txconf = &dev_info.default_txconf; + rxconf->rx_drop_en = 1; + + /* Enable vlan offload */ + txconf->txq_flags &= ~ETH_TXQ_FLAGS_NOVLANOFFL; + + /* + * Zero copy defers queue RX/TX start to the time when guest + * finishes its startup and packet buffers from that guest are + * available. + */ + if (zero_copy) { + rxconf->rx_deferred_start = 1; + rxconf->rx_drop_en = 0; + txconf->tx_deferred_start = 1; + } + /*configure the number of supported virtio devices based on VMDQ limits */ num_devices = dev_info.max_vmdq_pools; - num_queues = dev_info.max_rx_queues; + + if (zero_copy) { + rx_ring_size = num_rx_descriptor; + tx_ring_size = num_tx_descriptor; + tx_rings = dev_info.max_tx_queues; + } else { + rx_ring_size = RTE_TEST_RX_DESC_DEFAULT; + tx_ring_size = RTE_TEST_TX_DESC_DEFAULT; + tx_rings = (uint16_t)rte_lcore_count(); + } retval = validate_num_devices(MAX_DEVICES); if (retval < 0) @@ -345,10 +429,19 @@ port_init(uint8_t port, struct rte_mempool *mbuf_pool) retval = get_eth_conf(&port_conf, num_devices); if (retval < 0) return retval; + /* NIC queues are divided into pf queues and vmdq queues. */ + num_pf_queues = dev_info.max_rx_queues - dev_info.vmdq_queue_num; + queues_per_pool = dev_info.vmdq_queue_num / dev_info.max_vmdq_pools; + num_vmdq_queues = num_devices * queues_per_pool; + num_queues = num_pf_queues + num_vmdq_queues; + vmdq_queue_base = dev_info.vmdq_queue_base; + vmdq_pool_base = dev_info.vmdq_pool_base; + printf("pf queue num: %u, configured vmdq pool num: %u, each vmdq pool has %u queues\n", + num_pf_queues, num_devices, queues_per_pool); if (port >= rte_eth_dev_count()) return -1; - rx_rings = (uint16_t)num_queues, + rx_rings = (uint16_t)dev_info.max_rx_queues; /* Configure ethernet device. */ retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf); if (retval != 0) @@ -357,26 +450,33 @@ port_init(uint8_t port, struct rte_mempool *mbuf_pool) /* Setup the queues. */ for (q = 0; q < rx_rings; q ++) { retval = rte_eth_rx_queue_setup(port, q, rx_ring_size, - rte_eth_dev_socket_id(port), &rx_conf_default, - mbuf_pool); + rte_eth_dev_socket_id(port), + rxconf, + vpool_array[q].pool); if (retval < 0) return retval; } for (q = 0; q < tx_rings; q ++) { retval = rte_eth_tx_queue_setup(port, q, tx_ring_size, - rte_eth_dev_socket_id(port), &tx_conf_default); + rte_eth_dev_socket_id(port), + txconf); if (retval < 0) return retval; } /* Start the device. */ retval = rte_eth_dev_start(port); - if (retval < 0) + if (retval < 0) { + RTE_LOG(ERR, VHOST_DATA, "Failed to start the device.\n"); return retval; + } + + if (promiscuous) + rte_eth_promiscuous_enable(port); rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]); - RTE_LOG(INFO, PORT, "Max virtio devices supported: %u\n", num_devices); - RTE_LOG(INFO, PORT, "Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8 + RTE_LOG(INFO, VHOST_PORT, "Max virtio devices supported: %u\n", num_devices); + RTE_LOG(INFO, VHOST_PORT, "Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8 " %02"PRIx8" %02"PRIx8" %02"PRIx8"\n", (unsigned)port, vmdq_ports_eth_addr[port].addr_bytes[0], @@ -400,7 +500,7 @@ us_vhost_parse_basename(const char *q_arg) if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ) return -1; else - rte_snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg); + snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg); return 0; } @@ -457,16 +557,26 @@ parse_num_opt(const char *q_arg, uint32_t max_valid_value) static void us_vhost_usage(const char *prgname) { - RTE_LOG(INFO, CONFIG, "%s [EAL options] -- -p PORTMASK --vm2vm [0|1] --rx_retry [0|1] --mergeable [0|1] --stats [0-N] --dev-basename --dev-index [0-N] --nb-devices ND\n" + RTE_LOG(INFO, VHOST_CONFIG, "%s [EAL options] -- -p PORTMASK\n" + " --vm2vm [0|1|2]\n" + " --rx_retry [0|1] --mergeable [0|1] --stats [0-N]\n" + " --dev-basename \n" + " --nb-devices ND\n" " -p PORTMASK: Set mask for ports to be used by application\n" - " --vm2vm [0|1]: disable/enable(default) vm2vm comms\n" + " --vm2vm [0|1|2]: disable/software(default)/hardware vm2vm comms\n" " --rx-retry [0|1]: disable/enable(default) retries on rx. Enable retry if destintation queue is full\n" " --rx-retry-delay [0-N]: timeout(in usecond) between retries on RX. This makes effect only if retries on rx enabled\n" " --rx-retry-num [0-N]: the number of retries on rx. This makes effect only if retries on rx enabled\n" " --mergeable [0|1]: disable(default)/enable RX mergeable buffers\n" + " --vlan-strip [0|1]: disable/enable(default) RX VLAN strip on host\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" - " --dev-index [0-N]: Defaults to zero if not used. Index is appended to basename.\n", + " --zero-copy [0|1]: disable(default)/enable rx/tx " + "zero copy\n" + " --rx-desc-num [0-N]: the number of descriptors on rx, " + "used only when zero copy is enabled.\n" + " --tx-desc-num [0-N]: the number of descriptors on tx, " + "used only when zero copy is enabled.\n", prgname); } @@ -486,35 +596,51 @@ us_vhost_parse_args(int argc, char **argv) {"rx-retry-delay", required_argument, NULL, 0}, {"rx-retry-num", required_argument, NULL, 0}, {"mergeable", required_argument, NULL, 0}, + {"vlan-strip", required_argument, NULL, 0}, {"stats", required_argument, NULL, 0}, {"dev-basename", required_argument, NULL, 0}, - {"dev-index", required_argument, NULL, 0}, - {NULL, 0, 0, 0} + {"zero-copy", required_argument, NULL, 0}, + {"rx-desc-num", required_argument, NULL, 0}, + {"tx-desc-num", required_argument, NULL, 0}, + {NULL, 0, 0, 0}, }; /* Parse command line */ - while ((opt = getopt_long(argc, argv, "p:",long_option, &option_index)) != EOF) { + 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, CONFIG, "Invalid portmask\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid portmask\n"); us_vhost_usage(prgname); return -1; } break; + case 'P': + promiscuous = 1; + vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.rx_mode = + ETH_VMDQ_ACCEPT_BROADCAST | + ETH_VMDQ_ACCEPT_MULTICAST; + rte_vhost_feature_enable(1ULL << VIRTIO_NET_F_CTRL_RX); + + break; + case 0: /* Enable/disable vm2vm comms. */ - if (!strncmp(long_option[option_index].name, "vm2vm", MAX_LONG_OPT_SZ)) { - ret = parse_num_opt(optarg, 1); + if (!strncmp(long_option[option_index].name, "vm2vm", + MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, (VM2VM_LAST - 1)); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for vm2vm [0|1]\n"); + RTE_LOG(INFO, VHOST_CONFIG, + "Invalid argument for " + "vm2vm [0|1|2]\n"); us_vhost_usage(prgname); return -1; } else { - enable_vm2vm = ret; + vm2vm_mode = (vm2vm_type)ret; } } @@ -522,7 +648,7 @@ us_vhost_parse_args(int argc, char **argv) if (!strncmp(long_option[option_index].name, "rx-retry", MAX_LONG_OPT_SZ)) { ret = parse_num_opt(optarg, 1); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry [0|1]\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry [0|1]\n"); us_vhost_usage(prgname); return -1; } else { @@ -534,7 +660,7 @@ us_vhost_parse_args(int argc, char **argv) if (!strncmp(long_option[option_index].name, "rx-retry-delay", MAX_LONG_OPT_SZ)) { ret = parse_num_opt(optarg, INT32_MAX); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-delay [0-N]\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-delay [0-N]\n"); us_vhost_usage(prgname); return -1; } else { @@ -546,7 +672,7 @@ us_vhost_parse_args(int argc, char **argv) if (!strncmp(long_option[option_index].name, "rx-retry-num", MAX_LONG_OPT_SZ)) { ret = parse_num_opt(optarg, INT32_MAX); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-num [0-N]\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-num [0-N]\n"); us_vhost_usage(prgname); return -1; } else { @@ -558,12 +684,32 @@ us_vhost_parse_args(int argc, char **argv) if (!strncmp(long_option[option_index].name, "mergeable", MAX_LONG_OPT_SZ)) { ret = parse_num_opt(optarg, 1); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for mergeable [0|1]\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for mergeable [0|1]\n"); + us_vhost_usage(prgname); + return -1; + } else { + mergeable = !!ret; + if (ret) { + vmdq_conf_default.rxmode.jumbo_frame = 1; + vmdq_conf_default.rxmode.max_rx_pkt_len + = JUMBO_FRAME_MAX_SIZE; + } + } + } + + /* Enable/disable RX VLAN strip on host. */ + if (!strncmp(long_option[option_index].name, + "vlan-strip", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, 1); + if (ret == -1) { + RTE_LOG(INFO, VHOST_CONFIG, + "Invalid argument for VLAN strip [0|1]\n"); us_vhost_usage(prgname); return -1; } else { - if (ret) - VHOST_FEATURES = (1ULL << VIRTIO_NET_F_MRG_RXBUF); + vlan_strip = !!ret; + vmdq_conf_default.rxmode.hw_vlan_strip = + vlan_strip; } } @@ -571,7 +717,7 @@ us_vhost_parse_args(int argc, char **argv) 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, CONFIG, "Invalid argument for stats [0..N]\n"); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for stats [0..N]\n"); us_vhost_usage(prgname); return -1; } else { @@ -582,21 +728,53 @@ us_vhost_parse_args(int argc, char **argv) /* Set character device basename. */ if (!strncmp(long_option[option_index].name, "dev-basename", MAX_LONG_OPT_SZ)) { if (us_vhost_parse_basename(optarg) == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ); + RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ); us_vhost_usage(prgname); return -1; } } - /* Set character device index. */ - if (!strncmp(long_option[option_index].name, "dev-index", MAX_LONG_OPT_SZ)) { - ret = parse_num_opt(optarg, INT32_MAX); + /* Enable/disable rx/tx zero copy. */ + if (!strncmp(long_option[option_index].name, + "zero-copy", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, 1); if (ret == -1) { - RTE_LOG(INFO, CONFIG, "Invalid argument for character device index [0..N]\n"); + RTE_LOG(INFO, VHOST_CONFIG, + "Invalid argument" + " for zero-copy [0|1]\n"); + us_vhost_usage(prgname); + return -1; + } else + zero_copy = ret; + } + + /* Specify the descriptor number on RX. */ + if (!strncmp(long_option[option_index].name, + "rx-desc-num", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, MAX_RING_DESC); + if ((ret == -1) || (!POWEROF2(ret))) { + RTE_LOG(INFO, VHOST_CONFIG, + "Invalid argument for rx-desc-num[0-N]," + "power of 2 required.\n"); + us_vhost_usage(prgname); + return -1; + } else { + num_rx_descriptor = ret; + } + } + + /* Specify the descriptor number on TX. */ + if (!strncmp(long_option[option_index].name, + "tx-desc-num", MAX_LONG_OPT_SZ)) { + ret = parse_num_opt(optarg, MAX_RING_DESC); + if ((ret == -1) || (!POWEROF2(ret))) { + RTE_LOG(INFO, VHOST_CONFIG, + "Invalid argument for tx-desc-num [0-N]," + "power of 2 required.\n"); us_vhost_usage(prgname); return -1; } else { - dev_index = ret; + num_tx_descriptor = ret; } } @@ -615,11 +793,26 @@ us_vhost_parse_args(int argc, char **argv) } if ((num_ports == 0) || (num_ports > MAX_SUP_PORTS)) { - RTE_LOG(INFO, PORT, "Current enabled port number is %u," + 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; } + if ((zero_copy == 1) && (vm2vm_mode == VM2VM_SOFTWARE)) { + RTE_LOG(INFO, VHOST_PORT, + "Vhost zero copy doesn't support software vm2vm," + "please specify 'vm2vm 2' to use hardware vm2vm.\n"); + return -1; + } + + if ((zero_copy == 1) && (vmdq_conf_default.rxmode.jumbo_frame == 1)) { + RTE_LOG(INFO, VHOST_PORT, + "Vhost zero copy doesn't support jumbo frame," + "please specify '--mergeable 0' to disable the " + "mergeable feature.\n"); + return -1; + } + return 0; } @@ -633,14 +826,14 @@ static unsigned check_ports_num(unsigned nb_ports) unsigned portid; if (num_ports > nb_ports) { - RTE_LOG(INFO, PORT, "\nSpecified port number(%u) exceeds total system port number(%u)\n", + 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, PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n", + 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--; @@ -660,200 +853,54 @@ static unsigned check_ports_num(unsigned nb_ports) char packet[MAX_PRINT_BUFF]; \ \ if ((header)) \ - rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \ + snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \ else \ - rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \ + snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \ for (index = 0; index < (size); index++) { \ - rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \ + snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \ "%02hhx ", pkt_addr[index]); \ } \ - rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \ + snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \ \ - LOG_DEBUG(DATA, "%s", packet); \ + LOG_DEBUG(VHOST_DATA, "%s", packet); \ } while(0) #else #define PRINT_PACKET(device, addr, size, header) do{} while(0) #endif /* - * Function to convert guest physical addresses to vhost virtual addresses. This - * is used to convert virtio buffer addresses. + * Function to convert guest physical addresses to vhost physical addresses. + * This is used to convert virtio buffer addresses. */ static inline uint64_t __attribute__((always_inline)) -gpa_to_vva(struct virtio_net *dev, uint64_t guest_pa) +gpa_to_hpa(struct vhost_dev *vdev, uint64_t guest_pa, + uint32_t buf_len, hpa_type *addr_type) { - struct virtio_memory_regions *region; + struct virtio_memory_regions_hpa *region; uint32_t regionidx; - uint64_t vhost_va = 0; + uint64_t vhost_pa = 0; - for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) { - region = &dev->mem->regions[regionidx]; + *addr_type = PHYS_ADDR_INVALID; + + for (regionidx = 0; regionidx < vdev->nregions_hpa; regionidx++) { + region = &vdev->regions_hpa[regionidx]; if ((guest_pa >= region->guest_phys_address) && (guest_pa <= region->guest_phys_address_end)) { - vhost_va = region->address_offset + guest_pa; + vhost_pa = region->host_phys_addr_offset + guest_pa; + if (likely((guest_pa + buf_len - 1) + <= region->guest_phys_address_end)) + *addr_type = PHYS_ADDR_CONTINUOUS; + else + *addr_type = PHYS_ADDR_CROSS_SUBREG; break; } } - LOG_DEBUG(DATA, "(%"PRIu64") GPA %p| VVA %p\n", - dev->device_fh, (void*)(uintptr_t)guest_pa, (void*)(uintptr_t)vhost_va); - - return vhost_va; -} - -/* - * This function adds buffers to the virtio devices RX virtqueue. Buffers can - * be received from the physical port or from another virtio device. A packet - * count is returned to indicate the number of packets that were succesfully - * added to the RX queue. - */ -static inline uint32_t __attribute__((always_inline)) -virtio_dev_rx(struct virtio_net *dev, struct rte_mbuf **pkts, uint32_t count) -{ - struct vhost_virtqueue *vq; - struct vring_desc *desc; - struct rte_mbuf *buff; - /* The virtio_hdr is initialised to 0. */ - struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {{0,0,0,0,0,0},0}; - uint64_t buff_addr = 0; - uint64_t buff_hdr_addr = 0; - uint32_t head[MAX_PKT_BURST], packet_len = 0; - uint32_t head_idx, packet_success = 0; - uint32_t mergeable, mrg_count = 0; - uint32_t retry = 0; - uint16_t avail_idx, res_cur_idx; - uint16_t res_base_idx, res_end_idx; - uint16_t free_entries; - uint8_t success = 0; - - LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh); - vq = dev->virtqueue[VIRTIO_RXQ]; - count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count; - /* As many data cores may want access to available buffers, they need to be reserved. */ - do { - res_base_idx = vq->last_used_idx_res; - avail_idx = *((volatile uint16_t *)&vq->avail->idx); - - free_entries = (avail_idx - res_base_idx); - /* If retry is enabled and the queue is full then we wait and retry to avoid packet loss. */ - if (enable_retry && unlikely(count > free_entries)) { - for (retry = 0; retry < burst_rx_retry_num; retry++) { - rte_delay_us(burst_rx_delay_time); - avail_idx = - *((volatile uint16_t *)&vq->avail->idx); - free_entries = (avail_idx - res_base_idx); - if (count <= free_entries) - break; - } - } - - /*check that we have enough buffers*/ - if (unlikely(count > free_entries)) - count = free_entries; - - if (count == 0) - return 0; - - res_end_idx = res_base_idx + count; - /* vq->last_used_idx_res is atomically updated. */ - success = rte_atomic16_cmpset(&vq->last_used_idx_res, res_base_idx, - res_end_idx); - } while (unlikely(success == 0)); - res_cur_idx = res_base_idx; - LOG_DEBUG(DATA, "(%"PRIu64") Current Index %d| End Index %d\n", dev->device_fh, res_cur_idx, res_end_idx); - - /* Prefetch available ring to retrieve indexes. */ - rte_prefetch0(&vq->avail->ring[res_cur_idx & (vq->size - 1)]); - - /* Check if the VIRTIO_NET_F_MRG_RXBUF feature is enabled. */ - mergeable = dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF); - - /* Retrieve all of the head indexes first to avoid caching issues. */ - for (head_idx = 0; head_idx < count; head_idx++) - head[head_idx] = vq->avail->ring[(res_cur_idx + head_idx) & (vq->size - 1)]; - - /*Prefetch descriptor index. */ - rte_prefetch0(&vq->desc[head[packet_success]]); - - while (res_cur_idx != res_end_idx) { - /* Get descriptor from available ring */ - desc = &vq->desc[head[packet_success]]; - - buff = pkts[packet_success]; - - /* Convert from gpa to vva (guest physical addr -> vhost virtual addr) */ - buff_addr = gpa_to_vva(dev, desc->addr); - /* Prefetch buffer address. */ - rte_prefetch0((void*)(uintptr_t)buff_addr); - - if (mergeable && (mrg_count != 0)) { - desc->len = packet_len = rte_pktmbuf_data_len(buff); - } else { - /* Copy virtio_hdr to packet and increment buffer address */ - buff_hdr_addr = buff_addr; - packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen; - - /* - * If the descriptors are chained the header and data are placed in - * separate buffers. - */ - if (desc->flags & VRING_DESC_F_NEXT) { - desc->len = vq->vhost_hlen; - desc = &vq->desc[desc->next]; - /* Buffer address translation. */ - buff_addr = gpa_to_vva(dev, desc->addr); - desc->len = rte_pktmbuf_data_len(buff); - } else { - buff_addr += vq->vhost_hlen; - desc->len = packet_len; - } - } - - PRINT_PACKET(dev, (uintptr_t)buff_addr, rte_pktmbuf_data_len(buff), 0); - - /* Update used ring with desc information */ - vq->used->ring[res_cur_idx & (vq->size - 1)].id = head[packet_success]; - vq->used->ring[res_cur_idx & (vq->size - 1)].len = packet_len; - - /* Copy mbuf data to buffer */ - rte_memcpy((void *)(uintptr_t)buff_addr, (const void*)buff->pkt.data, rte_pktmbuf_data_len(buff)); - - res_cur_idx++; - packet_success++; - - /* If mergeable is disabled then a header is required per buffer. */ - if (!mergeable) { - rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen); - PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1); - } else { - mrg_count++; - /* Merge buffer can only handle so many buffers at a time. Tell the guest if this limit is reached. */ - if ((mrg_count == MAX_MRG_PKT_BURST) || (res_cur_idx == res_end_idx)) { - virtio_hdr.num_buffers = mrg_count; - LOG_DEBUG(DATA, "(%"PRIu64") RX: Num merge buffers %d\n", dev->device_fh, virtio_hdr.num_buffers); - rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen); - PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1); - mrg_count = 0; - } - } - if (res_cur_idx < res_end_idx) { - /* Prefetch descriptor index. */ - rte_prefetch0(&vq->desc[head[packet_success]]); - } - } - rte_compiler_barrier(); - - /* Wait until it's our turn to add our buffer to the used ring. */ - while (unlikely(vq->last_used_idx != res_base_idx)) - rte_pause(); - - *(volatile uint16_t *)&vq->used->idx += count; - vq->last_used_idx = res_end_idx; + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") GPA %p| HPA %p\n", + vdev->dev->device_fh, (void *)(uintptr_t)guest_pa, + (void *)(uintptr_t)vhost_pa); - /* Kick the guest if necessary. */ - if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) - eventfd_write((int)vq->kickfd, 1); - return count; + return vhost_pa; } /* @@ -870,51 +917,54 @@ ether_addr_cmp(struct ether_addr *ea, struct ether_addr *eb) * vlan tag to a VMDQ. */ static int -link_vmdq(struct virtio_net *dev, struct rte_mbuf *m) +link_vmdq(struct vhost_dev *vdev, struct rte_mbuf *m) { struct ether_hdr *pkt_hdr; struct virtio_net_data_ll *dev_ll; + struct virtio_net *dev = vdev->dev; int i, ret; /* Learn MAC address of guest device from packet */ - pkt_hdr = (struct ether_hdr *)m->pkt.data; + pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); dev_ll = ll_root_used; while (dev_ll != NULL) { - if (ether_addr_cmp(&(pkt_hdr->s_addr), &dev_ll->dev->mac_address)) { - RTE_LOG(INFO, DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh); + if (ether_addr_cmp(&(pkt_hdr->s_addr), &dev_ll->vdev->mac_address)) { + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh); return -1; } dev_ll = dev_ll->next; } for (i = 0; i < ETHER_ADDR_LEN; i++) - dev->mac_address.addr_bytes[i] = pkt_hdr->s_addr.addr_bytes[i]; + vdev->mac_address.addr_bytes[i] = pkt_hdr->s_addr.addr_bytes[i]; /* vlan_tag currently uses the device_id. */ - dev->vlan_tag = vlan_tags[dev->device_fh]; - dev->vmdq_rx_q = dev->device_fh * (num_queues/num_devices); + vdev->vlan_tag = vlan_tags[dev->device_fh]; /* Print out VMDQ registration info. */ - RTE_LOG(INFO, DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n", + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n", dev->device_fh, - dev->mac_address.addr_bytes[0], dev->mac_address.addr_bytes[1], - dev->mac_address.addr_bytes[2], dev->mac_address.addr_bytes[3], - dev->mac_address.addr_bytes[4], dev->mac_address.addr_bytes[5], - dev->vlan_tag); + vdev->mac_address.addr_bytes[0], vdev->mac_address.addr_bytes[1], + vdev->mac_address.addr_bytes[2], vdev->mac_address.addr_bytes[3], + vdev->mac_address.addr_bytes[4], vdev->mac_address.addr_bytes[5], + vdev->vlan_tag); /* Register the MAC address. */ - ret = rte_eth_dev_mac_addr_add(ports[0], &dev->mac_address, (uint32_t)dev->device_fh); + ret = rte_eth_dev_mac_addr_add(ports[0], &vdev->mac_address, + (uint32_t)dev->device_fh + vmdq_pool_base); if (ret) - RTE_LOG(ERR, DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n", + RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n", dev->device_fh); /* Enable stripping of the vlan tag as we handle routing. */ - rte_eth_dev_set_vlan_strip_on_queue(ports[0], (uint16_t)dev->vmdq_rx_q, 1); + if (vlan_strip) + rte_eth_dev_set_vlan_strip_on_queue(ports[0], + (uint16_t)vdev->vmdq_rx_q, 1); /* Set device as ready for RX. */ - dev->ready = DEVICE_RX; + vdev->ready = DEVICE_RX; return 0; } @@ -924,33 +974,33 @@ link_vmdq(struct virtio_net *dev, struct rte_mbuf *m) * queue before disabling RX on the device. */ static inline void -unlink_vmdq(struct virtio_net *dev) +unlink_vmdq(struct vhost_dev *vdev) { unsigned i = 0; unsigned rx_count; struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; - if (dev->ready == DEVICE_RX) { + if (vdev->ready == DEVICE_RX) { /*clear MAC and VLAN settings*/ - rte_eth_dev_mac_addr_remove(ports[0], &dev->mac_address); + rte_eth_dev_mac_addr_remove(ports[0], &vdev->mac_address); for (i = 0; i < 6; i++) - dev->mac_address.addr_bytes[i] = 0; + vdev->mac_address.addr_bytes[i] = 0; - dev->vlan_tag = 0; + vdev->vlan_tag = 0; /*Clear out the receive buffers*/ rx_count = rte_eth_rx_burst(ports[0], - (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); + (uint16_t)vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); while (rx_count) { for (i = 0; i < rx_count; i++) rte_pktmbuf_free(pkts_burst[i]); rx_count = rte_eth_rx_burst(ports[0], - (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); + (uint16_t)vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); } - dev->ready = DEVICE_MAC_LEARNING; + vdev->ready = DEVICE_MAC_LEARNING; } } @@ -958,43 +1008,50 @@ unlink_vmdq(struct virtio_net *dev) * Check if the packet destination MAC address is for a local device. If so then put * the packet on that devices RX queue. If not then return. */ -static inline unsigned __attribute__((always_inline)) -virtio_tx_local(struct virtio_net *dev, struct rte_mbuf *m) +static inline int __attribute__((always_inline)) +virtio_tx_local(struct vhost_dev *vdev, struct rte_mbuf *m) { struct virtio_net_data_ll *dev_ll; struct ether_hdr *pkt_hdr; uint64_t ret = 0; + struct virtio_net *dev = vdev->dev; + struct virtio_net *tdev; /* destination virito device */ - pkt_hdr = (struct ether_hdr *)m->pkt.data; + pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); /*get the used devices list*/ dev_ll = ll_root_used; while (dev_ll != NULL) { - if ((dev_ll->dev->ready == DEVICE_RX) && ether_addr_cmp(&(pkt_hdr->d_addr), - &dev_ll->dev->mac_address)) { + if ((dev_ll->vdev->ready == DEVICE_RX) && ether_addr_cmp(&(pkt_hdr->d_addr), + &dev_ll->vdev->mac_address)) { /* Drop the packet if the TX packet is destined for the TX device. */ - if (dev_ll->dev->device_fh == dev->device_fh) { - LOG_DEBUG(DATA, "(%"PRIu64") TX: Source and destination MAC addresses are the same. Dropping packet.\n", - dev_ll->dev->device_fh); + if (dev_ll->vdev->dev->device_fh == dev->device_fh) { + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: Source and destination MAC addresses are the same. Dropping packet.\n", + dev->device_fh); return 0; } + tdev = dev_ll->vdev->dev; - LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is local\n", dev_ll->dev->device_fh); + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is local\n", tdev->device_fh); - if (dev_ll->dev->remove) { + if (unlikely(dev_ll->vdev->remove)) { /*drop the packet if the device is marked for removal*/ - LOG_DEBUG(DATA, "(%"PRIu64") Device is marked for removal\n", dev_ll->dev->device_fh); + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", tdev->device_fh); } else { /*send the packet to the local virtio device*/ - ret = virtio_dev_rx(dev_ll->dev, &m, 1); + ret = rte_vhost_enqueue_burst(tdev, VIRTIO_RXQ, &m, 1); if (enable_stats) { - rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, 1); - rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret); - dev_statistics[dev->device_fh].tx_total++; - dev_statistics[dev->device_fh].tx += ret; + rte_atomic64_add( + &dev_statistics[tdev->device_fh].rx_total_atomic, + 1); + rte_atomic64_add( + &dev_statistics[tdev->device_fh].rx_atomic, + ret); + dev_statistics[tdev->device_fh].tx_total++; + dev_statistics[tdev->device_fh].tx += ret; } } @@ -1006,55 +1063,124 @@ virtio_tx_local(struct virtio_net *dev, struct rte_mbuf *m) return -1; } +/* + * Check if the destination MAC of a packet is one local VM, + * and get its vlan tag, and offset if it is. + */ +static inline int __attribute__((always_inline)) +find_local_dest(struct virtio_net *dev, struct rte_mbuf *m, + uint32_t *offset, uint16_t *vlan_tag) +{ + struct virtio_net_data_ll *dev_ll = ll_root_used; + struct ether_hdr *pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + + while (dev_ll != NULL) { + if ((dev_ll->vdev->ready == DEVICE_RX) + && ether_addr_cmp(&(pkt_hdr->d_addr), + &dev_ll->vdev->mac_address)) { + /* + * Drop the packet if the TX packet is + * destined for the TX device. + */ + if (dev_ll->vdev->dev->device_fh == dev->device_fh) { + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") TX: Source and destination" + " MAC addresses are the same. Dropping " + "packet.\n", + dev_ll->vdev->dev->device_fh); + return -1; + } + + /* + * HW vlan strip will reduce the packet length + * by minus length of vlan tag, so need restore + * the packet length by plus it. + */ + *offset = VLAN_HLEN; + *vlan_tag = + (uint16_t) + vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh]; + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") TX: pkt to local VM device id:" + "(%"PRIu64") vlan tag: %d.\n", + dev->device_fh, dev_ll->vdev->dev->device_fh, + vlan_tag); + + break; + } + dev_ll = dev_ll->next; + } + return 0; +} + /* * 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 virtio_net* dev, struct rte_mbuf *m, struct rte_mempool *mbuf_pool, uint16_t vlan_tag) +virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, uint16_t vlan_tag) { struct mbuf_table *tx_q; - struct vlan_ethhdr *vlan_hdr; struct rte_mbuf **m_table; - struct rte_mbuf *mbuf; - unsigned len, ret; + unsigned len, ret, offset = 0; const uint16_t lcore_id = rte_lcore_id(); + struct virtio_net *dev = vdev->dev; + struct ether_hdr *nh; /*check if destination is local VM*/ - if (enable_vm2vm && (virtio_tx_local(dev, m) == 0)) { + if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0)) { + rte_pktmbuf_free(m); return; } - LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh); + if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) { + if (unlikely(find_local_dest(dev, m, &offset, &vlan_tag) != 0)) { + rte_pktmbuf_free(m); + return; + } + } + + 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; - /* Allocate an mbuf and populate the structure. */ - mbuf = rte_pktmbuf_alloc(mbuf_pool); - if (unlikely(mbuf == NULL)) { - RTE_LOG(ERR, DATA, "Failed to allocate memory for mbuf.\n"); - return; - } + nh = rte_pktmbuf_mtod(m, struct ether_hdr *); + if (unlikely(nh->ether_type == rte_cpu_to_be_16(ETHER_TYPE_VLAN))) { + /* Guest has inserted the vlan tag. */ + struct vlan_hdr *vh = (struct vlan_hdr *) (nh + 1); + uint16_t vlan_tag_be = rte_cpu_to_be_16(vlan_tag); + if ((vm2vm_mode == VM2VM_HARDWARE) && + (vh->vlan_tci != vlan_tag_be)) + vh->vlan_tci = vlan_tag_be; + } else { + m->ol_flags = PKT_TX_VLAN_PKT; - mbuf->pkt.data_len = m->pkt.data_len + VLAN_HLEN; - mbuf->pkt.pkt_len = mbuf->pkt.data_len; + /* + * Find the right seg to adjust the data len when offset is + * bigger than tail room size. + */ + if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) { + if (likely(offset <= rte_pktmbuf_tailroom(m))) + m->data_len += offset; + else { + struct rte_mbuf *seg = m; - /* Copy ethernet header to mbuf. */ - rte_memcpy((void*)mbuf->pkt.data, (const void*)m->pkt.data, ETH_HLEN); + while ((seg->next != NULL) && + (offset > rte_pktmbuf_tailroom(seg))) + seg = seg->next; + seg->data_len += offset; + } + m->pkt_len += offset; + } - /* Setup vlan header. Bytes need to be re-ordered for network with htons()*/ - vlan_hdr = (struct vlan_ethhdr *) mbuf->pkt.data; - vlan_hdr->h_vlan_encapsulated_proto = vlan_hdr->h_vlan_proto; - vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q); - vlan_hdr->h_vlan_TCI = htons(vlan_tag); + m->vlan_tci = vlan_tag; + } - /* Copy the remaining packet contents to the mbuf. */ - rte_memcpy((void*) ((uint8_t*)mbuf->pkt.data + VLAN_ETH_HLEN), - (const void*) ((uint8_t*)m->pkt.data + ETH_HLEN), (m->pkt.data_len - ETH_HLEN)); - tx_q->m_table[len] = mbuf; + tx_q->m_table[len] = m; len++; if (enable_stats) { dev_statistics[dev->device_fh].tx_total++; @@ -1077,99 +1203,6 @@ virtio_tx_route(struct virtio_net* dev, struct rte_mbuf *m, struct rte_mempool * tx_q->len = len; return; } - -static inline void __attribute__((always_inline)) -virtio_dev_tx(struct virtio_net* dev, struct rte_mempool *mbuf_pool) -{ - struct rte_mbuf m; - struct vhost_virtqueue *vq; - struct vring_desc *desc; - uint64_t buff_addr = 0; - uint32_t head[MAX_PKT_BURST]; - uint32_t used_idx; - uint32_t i; - uint16_t free_entries, packet_success = 0; - uint16_t avail_idx; - - vq = dev->virtqueue[VIRTIO_TXQ]; - avail_idx = *((volatile uint16_t *)&vq->avail->idx); - - /* If there are no available buffers then return. */ - if (vq->last_used_idx == avail_idx) - return; - - LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh); - - /* Prefetch available ring to retrieve head indexes. */ - rte_prefetch0(&vq->avail->ring[vq->last_used_idx & (vq->size - 1)]); - - /*get the number of free entries in the ring*/ - free_entries = (avail_idx - vq->last_used_idx); - - /* Limit to MAX_PKT_BURST. */ - if (free_entries > MAX_PKT_BURST) - free_entries = MAX_PKT_BURST; - - LOG_DEBUG(DATA, "(%"PRIu64") Buffers available %d\n", dev->device_fh, free_entries); - /* Retrieve all of the head indexes first to avoid caching issues. */ - for (i = 0; i < free_entries; i++) - head[i] = vq->avail->ring[(vq->last_used_idx + i) & (vq->size - 1)]; - - /* Prefetch descriptor index. */ - rte_prefetch0(&vq->desc[head[packet_success]]); - rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]); - - while (packet_success < free_entries) { - desc = &vq->desc[head[packet_success]]; - - /* Discard first buffer as it is the virtio header */ - desc = &vq->desc[desc->next]; - - /* Buffer address translation. */ - buff_addr = gpa_to_vva(dev, desc->addr); - /* Prefetch buffer address. */ - rte_prefetch0((void*)(uintptr_t)buff_addr); - - used_idx = vq->last_used_idx & (vq->size - 1); - - if (packet_success < (free_entries - 1)) { - /* Prefetch descriptor index. */ - rte_prefetch0(&vq->desc[head[packet_success+1]]); - rte_prefetch0(&vq->used->ring[(used_idx + 1) & (vq->size - 1)]); - } - - /* Update used index buffer information. */ - vq->used->ring[used_idx].id = head[packet_success]; - vq->used->ring[used_idx].len = 0; - - /* Setup dummy mbuf. This is copied to a real mbuf if transmitted out the physical port. */ - m.pkt.data_len = desc->len; - m.pkt.data = (void*)(uintptr_t)buff_addr; - - PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0); - - /* If this is the first received packet we need to learn the MAC and setup VMDQ */ - if (dev->ready == DEVICE_MAC_LEARNING) { - if (dev->remove || (link_vmdq(dev, &m) == -1)) { - /*discard frame if device is scheduled for removal or a duplicate MAC address is found. */ - packet_success += free_entries; - vq->last_used_idx += packet_success; - break; - } - } - virtio_tx_route(dev, &m, mbuf_pool, (uint16_t)dev->device_fh); - - vq->last_used_idx++; - packet_success++; - } - - rte_compiler_barrier(); - vq->used->idx += packet_success; - /* Kick guest if required. */ - if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) - eventfd_write((int)vq->kickfd, 1); -} - /* * 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 @@ -1180,6 +1213,7 @@ 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 virtio_net_data_ll *dev_ll; struct mbuf_table *tx_q; @@ -1190,8 +1224,10 @@ switch_worker(__attribute__((unused)) void *arg) 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; + uint32_t retry = 0; - RTE_LOG(INFO, DATA, "Procesing on Core %u started \n", lcore_id); + RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id); lcore_ll = lcore_info[lcore_id].lcore_ll; prev_tsc = 0; @@ -1212,7 +1248,7 @@ switch_worker(__attribute__((unused)) void *arg) if (unlikely(diff_tsc > drain_tsc)) { if (tx_q->len) { - LOG_DEBUG(DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len); + LOG_DEBUG(VHOST_DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len); /*Tx any packets in the queue*/ ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id, @@ -1232,11 +1268,11 @@ switch_worker(__attribute__((unused)) void *arg) } 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) + if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL) lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL; /* @@ -1246,38 +1282,63 @@ switch_worker(__attribute__((unused)) void *arg) while (dev_ll != NULL) { /*get virtio device ID*/ - dev = dev_ll->dev; + vdev = dev_ll->vdev; + dev = vdev->dev; - if (dev->remove) { + if (unlikely(vdev->remove)) { dev_ll = dev_ll->next; - unlink_vmdq(dev); - dev->ready = DEVICE_SAFE_REMOVE; + unlink_vmdq(vdev); + vdev->ready = DEVICE_SAFE_REMOVE; continue; } - if (likely(dev->ready == DEVICE_RX)) { + if (likely(vdev->ready == DEVICE_RX)) { /*Handle guest RX*/ rx_count = rte_eth_rx_burst(ports[0], - (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); + vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST); if (rx_count) { - ret_count = virtio_dev_rx(dev, pkts_burst, rx_count); + /* + * Retry is enabled and the queue is full then we wait and retry to avoid packet loss + * Here MAX_PKT_BURST must be less than virtio queue size + */ + if (enable_retry && unlikely(rx_count > rte_vring_available_entries(dev, VIRTIO_RXQ))) { + for (retry = 0; retry < burst_rx_retry_num; retry++) { + rte_delay_us(burst_rx_delay_time); + if (rx_count <= rte_vring_available_entries(dev, VIRTIO_RXQ)) + break; + } + } + ret_count = rte_vhost_enqueue_burst(dev, VIRTIO_RXQ, pkts_burst, rx_count); if (enable_stats) { - rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, rx_count); - rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret_count); + 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_seg(pkts_burst[rx_count]); + rte_pktmbuf_free(pkts_burst[rx_count]); } } } - if (!dev->remove) - /*Handle guest TX*/ - virtio_dev_tx(dev, mbuf_pool); - - /*move to the next device in the list*/ + 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 and setup VMDQ */ + if (unlikely(vdev->ready == DEVICE_MAC_LEARNING) && tx_count) { + if (vdev->remove || (link_vmdq(vdev, pkts_burst[0]) == -1)) { + while (tx_count) + rte_pktmbuf_free(pkts_burst[--tx_count]); + } + } + while (tx_count) + virtio_tx_route(vdev, pkts_burst[--tx_count], (uint16_t)dev->device_fh); + } + + /*move to the next device in the list*/ dev_ll = dev_ll->next; } } @@ -1286,11 +1347,836 @@ switch_worker(__attribute__((unused)) void *arg) } /* - * 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(); + * This function gets available ring number for zero copy rx. + * Only one thread will call this funciton for a paticular virtio device, + * so, it is designed as non-thread-safe function. + */ +static inline uint32_t __attribute__((always_inline)) +get_available_ring_num_zcp(struct virtio_net *dev) +{ + struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ]; + uint16_t avail_idx; + + avail_idx = *((volatile uint16_t *)&vq->avail->idx); + return (uint32_t)(avail_idx - vq->last_used_idx_res); +} + +/* + * This function gets available ring index for zero copy rx, + * it will retry 'burst_rx_retry_num' times till it get enough ring index. + * Only one thread will call this funciton for a paticular virtio device, + * so, it is designed as non-thread-safe function. + */ +static inline uint32_t __attribute__((always_inline)) +get_available_ring_index_zcp(struct virtio_net *dev, + uint16_t *res_base_idx, uint32_t count) +{ + struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ]; + uint16_t avail_idx; + uint32_t retry = 0; + uint16_t free_entries; + + *res_base_idx = vq->last_used_idx_res; + avail_idx = *((volatile uint16_t *)&vq->avail->idx); + free_entries = (avail_idx - *res_base_idx); + + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") in get_available_ring_index_zcp: " + "avail idx: %d, " + "res base idx:%d, free entries:%d\n", + dev->device_fh, avail_idx, *res_base_idx, + free_entries); + + /* + * If retry is enabled and the queue is full then we wait + * and retry to avoid packet loss. + */ + if (enable_retry && unlikely(count > free_entries)) { + for (retry = 0; retry < burst_rx_retry_num; retry++) { + rte_delay_us(burst_rx_delay_time); + avail_idx = *((volatile uint16_t *)&vq->avail->idx); + free_entries = (avail_idx - *res_base_idx); + if (count <= free_entries) + break; + } + } + + /*check that we have enough buffers*/ + if (unlikely(count > free_entries)) + count = free_entries; + + if (unlikely(count == 0)) { + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") Fail in get_available_ring_index_zcp: " + "avail idx: %d, res base idx:%d, free entries:%d\n", + dev->device_fh, avail_idx, + *res_base_idx, free_entries); + return 0; + } + + vq->last_used_idx_res = *res_base_idx + count; + + return count; +} + +/* + * This function put descriptor back to used list. + */ +static inline void __attribute__((always_inline)) +put_desc_to_used_list_zcp(struct vhost_virtqueue *vq, uint16_t desc_idx) +{ + uint16_t res_cur_idx = vq->last_used_idx; + vq->used->ring[res_cur_idx & (vq->size - 1)].id = (uint32_t)desc_idx; + vq->used->ring[res_cur_idx & (vq->size - 1)].len = 0; + rte_compiler_barrier(); + *(volatile uint16_t *)&vq->used->idx += 1; + vq->last_used_idx += 1; + + /* Kick the guest if necessary. */ + if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) + eventfd_write((int)vq->callfd, 1); +} + +/* + * This function get available descriptor from vitio vring and un-attached mbuf + * from vpool->ring, and then attach them together. It needs adjust the offset + * for buff_addr and phys_addr accroding to PMD implementation, otherwise the + * frame data may be put to wrong location in mbuf. + */ +static inline void __attribute__((always_inline)) +attach_rxmbuf_zcp(struct virtio_net *dev) +{ + uint16_t res_base_idx, desc_idx; + uint64_t buff_addr, phys_addr; + struct vhost_virtqueue *vq; + struct vring_desc *desc; + struct rte_mbuf *mbuf = NULL; + struct vpool *vpool; + hpa_type addr_type; + struct vhost_dev *vdev = (struct vhost_dev *)dev->priv; + + vpool = &vpool_array[vdev->vmdq_rx_q]; + vq = dev->virtqueue[VIRTIO_RXQ]; + + do { + if (unlikely(get_available_ring_index_zcp(vdev->dev, &res_base_idx, + 1) != 1)) + return; + desc_idx = vq->avail->ring[(res_base_idx) & (vq->size - 1)]; + + desc = &vq->desc[desc_idx]; + if (desc->flags & VRING_DESC_F_NEXT) { + desc = &vq->desc[desc->next]; + buff_addr = gpa_to_vva(dev, desc->addr); + phys_addr = gpa_to_hpa(vdev, desc->addr, desc->len, + &addr_type); + } else { + buff_addr = gpa_to_vva(dev, + desc->addr + vq->vhost_hlen); + phys_addr = gpa_to_hpa(vdev, + desc->addr + vq->vhost_hlen, + desc->len, &addr_type); + } + + if (unlikely(addr_type == PHYS_ADDR_INVALID)) { + RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Invalid frame buffer" + " address found when attaching RX frame buffer" + " address!\n", dev->device_fh); + put_desc_to_used_list_zcp(vq, desc_idx); + continue; + } + + /* + * Check if the frame buffer address from guest crosses + * sub-region or not. + */ + if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) { + RTE_LOG(ERR, VHOST_DATA, + "(%"PRIu64") Frame buffer address cross " + "sub-regioin found when attaching RX frame " + "buffer address!\n", + dev->device_fh); + put_desc_to_used_list_zcp(vq, desc_idx); + continue; + } + } while (unlikely(phys_addr == 0)); + + rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf); + if (unlikely(mbuf == NULL)) { + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in attach_rxmbuf_zcp: " + "ring_sc_dequeue fail.\n", + dev->device_fh); + put_desc_to_used_list_zcp(vq, desc_idx); + return; + } + + if (unlikely(vpool->buf_size > desc->len)) { + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in attach_rxmbuf_zcp: frame buffer " + "length(%d) of descriptor idx: %d less than room " + "size required: %d\n", + dev->device_fh, desc->len, desc_idx, vpool->buf_size); + put_desc_to_used_list_zcp(vq, desc_idx); + rte_ring_sp_enqueue(vpool->ring, (void *)mbuf); + return; + } + + mbuf->buf_addr = (void *)(uintptr_t)(buff_addr - RTE_PKTMBUF_HEADROOM); + mbuf->data_off = RTE_PKTMBUF_HEADROOM; + mbuf->buf_physaddr = phys_addr - RTE_PKTMBUF_HEADROOM; + mbuf->data_len = desc->len; + MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx; + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in attach_rxmbuf_zcp: res base idx:%d, " + "descriptor idx:%d\n", + dev->device_fh, res_base_idx, desc_idx); + + __rte_mbuf_raw_free(mbuf); + + return; +} + +/* + * Detach an attched packet mbuf - + * - restore original mbuf address and length values. + * - reset pktmbuf data and data_len to their default values. + * All other fields of the given packet mbuf will be left intact. + * + * @param m + * The attached packet mbuf. + */ +static inline void pktmbuf_detach_zcp(struct rte_mbuf *m) +{ + const struct rte_mempool *mp = m->pool; + void *buf = RTE_MBUF_TO_BADDR(m); + uint32_t buf_ofs; + uint32_t buf_len = mp->elt_size - sizeof(*m); + m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof(*m); + + m->buf_addr = buf; + m->buf_len = (uint16_t)buf_len; + + buf_ofs = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? + RTE_PKTMBUF_HEADROOM : m->buf_len; + m->data_off = buf_ofs; + + m->data_len = 0; +} + +/* + * This function is called after packets have been transimited. It fetchs mbuf + * from vpool->pool, detached it and put into vpool->ring. It also update the + * used index and kick the guest if necessary. + */ +static inline uint32_t __attribute__((always_inline)) +txmbuf_clean_zcp(struct virtio_net *dev, struct vpool *vpool) +{ + struct rte_mbuf *mbuf; + struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ]; + uint32_t used_idx = vq->last_used_idx & (vq->size - 1); + uint32_t index = 0; + uint32_t mbuf_count = rte_mempool_count(vpool->pool); + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool before " + "clean is: %d\n", + dev->device_fh, mbuf_count); + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring before " + "clean is : %d\n", + dev->device_fh, rte_ring_count(vpool->ring)); + + for (index = 0; index < mbuf_count; index++) { + mbuf = __rte_mbuf_raw_alloc(vpool->pool); + if (likely(MBUF_EXT_MEM(mbuf))) + pktmbuf_detach_zcp(mbuf); + rte_ring_sp_enqueue(vpool->ring, mbuf); + + /* Update used index buffer information. */ + vq->used->ring[used_idx].id = MBUF_HEADROOM_UINT32(mbuf); + vq->used->ring[used_idx].len = 0; + + used_idx = (used_idx + 1) & (vq->size - 1); + } + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool after " + "clean is: %d\n", + dev->device_fh, rte_mempool_count(vpool->pool)); + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring after " + "clean is : %d\n", + dev->device_fh, rte_ring_count(vpool->ring)); + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: before updated " + "vq->last_used_idx:%d\n", + dev->device_fh, vq->last_used_idx); + + vq->last_used_idx += mbuf_count; + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in txmbuf_clean_zcp: after updated " + "vq->last_used_idx:%d\n", + dev->device_fh, vq->last_used_idx); + + rte_compiler_barrier(); + + *(volatile uint16_t *)&vq->used->idx += mbuf_count; + + /* Kick guest if required. */ + if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) + eventfd_write((int)vq->callfd, 1); + + return 0; +} + +/* + * This function is called when a virtio device is destroy. + * It fetchs mbuf from vpool->pool, and detached it, and put into vpool->ring. + */ +static void mbuf_destroy_zcp(struct vpool *vpool) +{ + struct rte_mbuf *mbuf = NULL; + uint32_t index, mbuf_count = rte_mempool_count(vpool->pool); + + LOG_DEBUG(VHOST_CONFIG, + "in mbuf_destroy_zcp: mbuf count in mempool before " + "mbuf_destroy_zcp is: %d\n", + mbuf_count); + LOG_DEBUG(VHOST_CONFIG, + "in mbuf_destroy_zcp: mbuf count in ring before " + "mbuf_destroy_zcp is : %d\n", + rte_ring_count(vpool->ring)); + + for (index = 0; index < mbuf_count; index++) { + mbuf = __rte_mbuf_raw_alloc(vpool->pool); + if (likely(mbuf != NULL)) { + if (likely(MBUF_EXT_MEM(mbuf))) + pktmbuf_detach_zcp(mbuf); + rte_ring_sp_enqueue(vpool->ring, (void *)mbuf); + } + } + + LOG_DEBUG(VHOST_CONFIG, + "in mbuf_destroy_zcp: mbuf count in mempool after " + "mbuf_destroy_zcp is: %d\n", + rte_mempool_count(vpool->pool)); + LOG_DEBUG(VHOST_CONFIG, + "in mbuf_destroy_zcp: mbuf count in ring after " + "mbuf_destroy_zcp is : %d\n", + rte_ring_count(vpool->ring)); +} + +/* + * This function update the use flag and counter. + */ +static inline uint32_t __attribute__((always_inline)) +virtio_dev_rx_zcp(struct virtio_net *dev, struct rte_mbuf **pkts, + uint32_t count) +{ + struct vhost_virtqueue *vq; + struct vring_desc *desc; + struct rte_mbuf *buff; + /* The virtio_hdr is initialised to 0. */ + struct virtio_net_hdr_mrg_rxbuf virtio_hdr + = {{0, 0, 0, 0, 0, 0}, 0}; + uint64_t buff_hdr_addr = 0; + uint32_t head[MAX_PKT_BURST], packet_len = 0; + uint32_t head_idx, packet_success = 0; + uint16_t res_cur_idx; + + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh); + + if (count == 0) + return 0; + + vq = dev->virtqueue[VIRTIO_RXQ]; + count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count; + + res_cur_idx = vq->last_used_idx; + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| End Index %d\n", + dev->device_fh, res_cur_idx, res_cur_idx + count); + + /* Retrieve all of the head indexes first to avoid caching issues. */ + for (head_idx = 0; head_idx < count; head_idx++) + head[head_idx] = MBUF_HEADROOM_UINT32(pkts[head_idx]); + + /*Prefetch descriptor index. */ + rte_prefetch0(&vq->desc[head[packet_success]]); + + while (packet_success != count) { + /* Get descriptor from available ring */ + desc = &vq->desc[head[packet_success]]; + + buff = pkts[packet_success]; + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in dev_rx_zcp: update the used idx for " + "pkt[%d] descriptor idx: %d\n", + dev->device_fh, packet_success, + MBUF_HEADROOM_UINT32(buff)); + + PRINT_PACKET(dev, + (uintptr_t)(((uint64_t)(uintptr_t)buff->buf_addr) + + RTE_PKTMBUF_HEADROOM), + rte_pktmbuf_data_len(buff), 0); + + /* Buffer address translation for virtio header. */ + buff_hdr_addr = gpa_to_vva(dev, desc->addr); + packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen; + + /* + * If the descriptors are chained the header and data are + * placed in separate buffers. + */ + if (desc->flags & VRING_DESC_F_NEXT) { + desc->len = vq->vhost_hlen; + desc = &vq->desc[desc->next]; + desc->len = rte_pktmbuf_data_len(buff); + } else { + desc->len = packet_len; + } + + /* Update used ring with desc information */ + vq->used->ring[res_cur_idx & (vq->size - 1)].id + = head[packet_success]; + vq->used->ring[res_cur_idx & (vq->size - 1)].len + = packet_len; + res_cur_idx++; + packet_success++; + + /* A header is required per buffer. */ + rte_memcpy((void *)(uintptr_t)buff_hdr_addr, + (const void *)&virtio_hdr, vq->vhost_hlen); + + PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1); + + if (likely(packet_success < count)) { + /* Prefetch descriptor index. */ + rte_prefetch0(&vq->desc[head[packet_success]]); + } + } + + rte_compiler_barrier(); + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in dev_rx_zcp: before update used idx: " + "vq.last_used_idx: %d, vq->used->idx: %d\n", + dev->device_fh, vq->last_used_idx, vq->used->idx); + + *(volatile uint16_t *)&vq->used->idx += count; + vq->last_used_idx += count; + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in dev_rx_zcp: after update used idx: " + "vq.last_used_idx: %d, vq->used->idx: %d\n", + dev->device_fh, vq->last_used_idx, vq->used->idx); + + /* Kick the guest if necessary. */ + if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) + eventfd_write((int)vq->callfd, 1); + + return count; +} + +/* + * 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_zcp(struct virtio_net *dev, struct rte_mbuf *m, + uint32_t desc_idx, uint8_t need_copy) +{ + struct mbuf_table *tx_q; + struct rte_mbuf **m_table; + struct rte_mbuf *mbuf = NULL; + unsigned len, ret, offset = 0; + struct vpool *vpool; + uint16_t vlan_tag = (uint16_t)vlan_tags[(uint16_t)dev->device_fh]; + uint16_t vmdq_rx_q = ((struct vhost_dev *)dev->priv)->vmdq_rx_q; + + /*Add packet to the port tx queue*/ + tx_q = &tx_queue_zcp[vmdq_rx_q]; + len = tx_q->len; + + /* Allocate an mbuf and populate the structure. */ + vpool = &vpool_array[MAX_QUEUES + vmdq_rx_q]; + rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf); + if (unlikely(mbuf == NULL)) { + struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ]; + RTE_LOG(ERR, VHOST_DATA, + "(%"PRIu64") Failed to allocate memory for mbuf.\n", + dev->device_fh); + put_desc_to_used_list_zcp(vq, desc_idx); + return; + } + + if (vm2vm_mode == VM2VM_HARDWARE) { + /* Avoid using a vlan tag from any vm for external pkt, such as + * vlan_tags[dev->device_fh], oterwise, it conflicts when pool + * selection, MAC address determines it as an external pkt + * which should go to network, while vlan tag determine it as + * a vm2vm pkt should forward to another vm. Hardware confuse + * such a ambiguous situation, so pkt will lost. + */ + vlan_tag = external_pkt_default_vlan_tag; + if (find_local_dest(dev, m, &offset, &vlan_tag) != 0) { + MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx; + __rte_mbuf_raw_free(mbuf); + return; + } + } + + mbuf->nb_segs = m->nb_segs; + mbuf->next = m->next; + mbuf->data_len = m->data_len + offset; + mbuf->pkt_len = mbuf->data_len; + if (unlikely(need_copy)) { + /* Copy the packet contents to the mbuf. */ + rte_memcpy(rte_pktmbuf_mtod(mbuf, void *), + rte_pktmbuf_mtod(m, void *), + m->data_len); + } else { + mbuf->data_off = m->data_off; + mbuf->buf_physaddr = m->buf_physaddr; + mbuf->buf_addr = m->buf_addr; + } + mbuf->ol_flags = PKT_TX_VLAN_PKT; + mbuf->vlan_tci = vlan_tag; + mbuf->l2_len = sizeof(struct ether_hdr); + mbuf->l3_len = sizeof(struct ipv4_hdr); + MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx; + + tx_q->m_table[len] = mbuf; + len++; + + LOG_DEBUG(VHOST_DATA, + "(%"PRIu64") in tx_route_zcp: pkt: nb_seg: %d, next:%s\n", + dev->device_fh, + mbuf->nb_segs, + (mbuf->next == NULL) ? "null" : "non-null"); + + 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; + ret = rte_eth_tx_burst(ports[0], + (uint16_t)tx_q->txq_id, m_table, (uint16_t) len); + + /* + * 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; + txmbuf_clean_zcp(dev, vpool); + } + + tx_q->len = len; + + return; +} + +/* + * This function TX all available packets in virtio TX queue for one + * virtio-net device. If it is first packet, it learns MAC address and + * setup VMDQ. + */ +static inline void __attribute__((always_inline)) +virtio_dev_tx_zcp(struct virtio_net *dev) +{ + struct rte_mbuf m; + struct vhost_virtqueue *vq; + struct vring_desc *desc; + uint64_t buff_addr = 0, phys_addr; + uint32_t head[MAX_PKT_BURST]; + uint32_t i; + uint16_t free_entries, packet_success = 0; + uint16_t avail_idx; + uint8_t need_copy = 0; + hpa_type addr_type; + struct vhost_dev *vdev = (struct vhost_dev *)dev->priv; + + vq = dev->virtqueue[VIRTIO_TXQ]; + avail_idx = *((volatile uint16_t *)&vq->avail->idx); + + /* If there are no available buffers then return. */ + if (vq->last_used_idx_res == avail_idx) + return; + + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh); + + /* Prefetch available ring to retrieve head indexes. */ + rte_prefetch0(&vq->avail->ring[vq->last_used_idx_res & (vq->size - 1)]); + + /* Get the number of free entries in the ring */ + free_entries = (avail_idx - vq->last_used_idx_res); + + /* Limit to MAX_PKT_BURST. */ + free_entries + = (free_entries > MAX_PKT_BURST) ? MAX_PKT_BURST : free_entries; + + LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n", + dev->device_fh, free_entries); + + /* Retrieve all of the head indexes first to avoid caching issues. */ + for (i = 0; i < free_entries; i++) + head[i] + = vq->avail->ring[(vq->last_used_idx_res + i) + & (vq->size - 1)]; + + vq->last_used_idx_res += free_entries; + + /* Prefetch descriptor index. */ + rte_prefetch0(&vq->desc[head[packet_success]]); + rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]); + + while (packet_success < free_entries) { + desc = &vq->desc[head[packet_success]]; + + /* Discard first buffer as it is the virtio header */ + desc = &vq->desc[desc->next]; + + /* Buffer address translation. */ + buff_addr = gpa_to_vva(dev, desc->addr); + /* Need check extra VLAN_HLEN size for inserting VLAN tag */ + phys_addr = gpa_to_hpa(vdev, desc->addr, desc->len + VLAN_HLEN, + &addr_type); + + if (likely(packet_success < (free_entries - 1))) + /* Prefetch descriptor index. */ + rte_prefetch0(&vq->desc[head[packet_success + 1]]); + + if (unlikely(addr_type == PHYS_ADDR_INVALID)) { + RTE_LOG(ERR, VHOST_DATA, + "(%"PRIu64") Invalid frame buffer address found" + "when TX packets!\n", + dev->device_fh); + packet_success++; + continue; + } + + /* Prefetch buffer address. */ + rte_prefetch0((void *)(uintptr_t)buff_addr); + + /* + * Setup dummy mbuf. This is copied to a real mbuf if + * transmitted out the physical port. + */ + m.data_len = desc->len; + m.nb_segs = 1; + m.next = NULL; + m.data_off = 0; + m.buf_addr = (void *)(uintptr_t)buff_addr; + m.buf_physaddr = phys_addr; + + /* + * Check if the frame buffer address from guest crosses + * sub-region or not. + */ + if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) { + RTE_LOG(ERR, VHOST_DATA, + "(%"PRIu64") Frame buffer address cross " + "sub-regioin found when attaching TX frame " + "buffer address!\n", + dev->device_fh); + need_copy = 1; + } else + need_copy = 0; + + PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0); + + /* + * If this is the first received packet we need to learn + * the MAC and setup VMDQ + */ + if (unlikely(vdev->ready == DEVICE_MAC_LEARNING)) { + if (vdev->remove || (link_vmdq(vdev, &m) == -1)) { + /* + * Discard frame if device is scheduled for + * removal or a duplicate MAC address is found. + */ + packet_success += free_entries; + vq->last_used_idx += packet_success; + break; + } + } + + virtio_tx_route_zcp(dev, &m, head[packet_success], need_copy); + packet_success++; + } +} + +/* + * 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_zcp(__attribute__((unused)) void *arg) +{ + struct virtio_net *dev = NULL; + struct vhost_dev *vdev = NULL; + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + 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; + const uint16_t lcore_id = rte_lcore_id(); + uint16_t count_in_ring, rx_count = 0; + + RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id); + + lcore_ll = lcore_info[lcore_id].lcore_ll; + prev_tsc = 0; + + while (1) { + cur_tsc = rte_rdtsc(); + + /* TX burst queue drain */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + /* + * Get mbuf from vpool.pool and detach mbuf and + * put back into vpool.ring. + */ + dev_ll = lcore_ll->ll_root_used; + while ((dev_ll != NULL) && (dev_ll->vdev != NULL)) { + /* Get virtio device ID */ + vdev = dev_ll->vdev; + dev = vdev->dev; + + if (likely(!vdev->remove)) { + tx_q = &tx_queue_zcp[(uint16_t)vdev->vmdq_rx_q]; + if (tx_q->len) { + LOG_DEBUG(VHOST_DATA, + "TX queue drained after timeout" + " with burst size %u\n", + tx_q->len); + + /* + * Tx any packets in the queue + */ + ret = rte_eth_tx_burst( + ports[0], + (uint16_t)tx_q->txq_id, + (struct rte_mbuf **) + tx_q->m_table, + (uint16_t)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; + + txmbuf_clean_zcp(dev, + &vpool_array[MAX_QUEUES+vdev->vmdq_rx_q]); + } + } + dev_ll = dev_ll->next; + } + 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) && (dev_ll->vdev != NULL)) { + vdev = dev_ll->vdev; + dev = vdev->dev; + if (unlikely(vdev->remove)) { + dev_ll = dev_ll->next; + unlink_vmdq(vdev); + vdev->ready = DEVICE_SAFE_REMOVE; + continue; + } + + if (likely(vdev->ready == DEVICE_RX)) { + uint32_t index = vdev->vmdq_rx_q; + uint16_t i; + count_in_ring + = rte_ring_count(vpool_array[index].ring); + uint16_t free_entries + = (uint16_t)get_available_ring_num_zcp(dev); + + /* + * Attach all mbufs in vpool.ring and put back + * into vpool.pool. + */ + for (i = 0; + i < RTE_MIN(free_entries, + RTE_MIN(count_in_ring, MAX_PKT_BURST)); + i++) + attach_rxmbuf_zcp(dev); + + /* Handle guest RX */ + rx_count = rte_eth_rx_burst(ports[0], + vdev->vmdq_rx_q, pkts_burst, + MAX_PKT_BURST); + + if (rx_count) { + ret_count = virtio_dev_rx_zcp(dev, + pkts_burst, rx_count); + if (enable_stats) { + dev_statistics[dev->device_fh].rx_total + += rx_count; + dev_statistics[dev->device_fh].rx + += ret_count; + } + while (likely(rx_count)) { + rx_count--; + pktmbuf_detach_zcp( + pkts_burst[rx_count]); + rte_ring_sp_enqueue( + vpool_array[index].ring, + (void *)pkts_burst[rx_count]); + } + } + } + + if (likely(!vdev->remove)) + /* Handle guest TX */ + virtio_dev_tx_zcp(dev); + + /* 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) +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; @@ -1311,14 +2197,16 @@ add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_da } /* - * 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(). + * 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) +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; @@ -1328,7 +2216,7 @@ rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_dat if (likely(ll_dev_last != NULL)) ll_dev_last->next = ll_dev->next; else - RTE_LOG(ERR, CONFIG, "Remove entry form ll failed.\n"); + RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n"); } /* @@ -1353,7 +2241,8 @@ get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr) * 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) +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; @@ -1376,12 +2265,12 @@ alloc_data_ll(uint32_t size) /* Malloc and then chain the linked list. */ ll_new = malloc(size * sizeof(struct virtio_net_data_ll)); if (ll_new == NULL) { - RTE_LOG(ERR, CONFIG, "Failed to allocate memory for ll_new.\n"); + 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].dev = NULL; + ll_new[i].vdev = NULL; ll_new[i].next = &ll_new[i+1]; } ll_new[i].next = NULL; @@ -1401,7 +2290,7 @@ init_data_ll (void) 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, CONFIG, "Failed to allocate memory for lcore_ll.\n"); + RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n"); return -1; } @@ -1421,18 +2310,8 @@ init_data_ll (void) } /* - * Set virtqueue flags so that we do not receive interrupts. - */ -static void -set_irq_status (struct virtio_net *dev) -{ - dev->virtqueue[VIRTIO_RXQ]->used->flags = VRING_USED_F_NO_NOTIFY; - dev->virtqueue[VIRTIO_TXQ]->used->flags = VRING_USED_F_NO_NOTIFY; -} - -/* - * 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 + * 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 @@ -1442,21 +2321,22 @@ destroy_device (volatile struct virtio_net *dev) 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. */ - dev->remove = 1; - - while(dev->ready != DEVICE_SAFE_REMOVE) { + 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[dev->coreid].lcore_ll->ll_root_used; + ll_lcore_dev_cur = lcore_info[vdev->coreid].lcore_ll->ll_root_used; while (ll_lcore_dev_cur != NULL) { - if (ll_lcore_dev_cur->dev == dev) { + if (ll_lcore_dev_cur->vdev == vdev) { break; } else { ll_lcore_dev_last = ll_lcore_dev_cur; @@ -1465,7 +2345,9 @@ destroy_device (volatile struct virtio_net *dev) } if (ll_lcore_dev_cur == NULL) { - RTE_LOG(ERR, CONFIG, "Failed to find the dev to be destroy.\n"); + RTE_LOG(ERR, VHOST_CONFIG, + "(%"PRIu64") Failed to find the dev to be destroy.\n", + dev->device_fh); return; } @@ -1473,7 +2355,7 @@ destroy_device (volatile struct virtio_net *dev) ll_main_dev_cur = ll_root_used; ll_main_dev_last = NULL; while (ll_main_dev_cur != NULL) { - if (ll_main_dev_cur->dev == dev) { + if (ll_main_dev_cur->vdev == vdev) { break; } else { ll_main_dev_last = ll_main_dev_cur; @@ -1482,15 +2364,15 @@ destroy_device (volatile struct virtio_net *dev) } /* Remove entries from the lcore and main ll. */ - rm_data_ll_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_used, ll_lcore_dev_cur, ll_lcore_dev_last); + 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. @@ -1502,13 +2384,201 @@ destroy_device (volatile struct virtio_net *dev) } /* Add the entries back to the lcore and main free ll.*/ - put_data_ll_free_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur); + 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[ll_lcore_dev_cur->dev->coreid].lcore_ll->device_num--; - - RTE_LOG(INFO, DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh); + 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); + + if (zero_copy) { + struct vpool *vpool = &vpool_array[vdev->vmdq_rx_q]; + + /* Stop the RX queue. */ + if (rte_eth_dev_rx_queue_stop(ports[0], vdev->vmdq_rx_q) != 0) { + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") In destroy_device: Failed to stop " + "rx queue:%d\n", + dev->device_fh, + vdev->vmdq_rx_q); + } + + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") in destroy_device: Start put mbuf in " + "mempool back to ring for RX queue: %d\n", + dev->device_fh, vdev->vmdq_rx_q); + + mbuf_destroy_zcp(vpool); + + /* Stop the TX queue. */ + if (rte_eth_dev_tx_queue_stop(ports[0], vdev->vmdq_rx_q) != 0) { + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") In destroy_device: Failed to " + "stop tx queue:%d\n", + dev->device_fh, vdev->vmdq_rx_q); + } + + vpool = &vpool_array[vdev->vmdq_rx_q + MAX_QUEUES]; + + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") destroy_device: Start put mbuf in mempool " + "back to ring for TX queue: %d, dev:(%"PRIu64")\n", + dev->device_fh, (vdev->vmdq_rx_q + MAX_QUEUES), + dev->device_fh); + + mbuf_destroy_zcp(vpool); + rte_free(vdev->regions_hpa); + } + rte_free(vdev); + +} + +/* + * Calculate the region count of physical continous regions for one particular + * region of whose vhost virtual address is continous. The particular region + * start from vva_start, with size of 'size' in argument. + */ +static uint32_t +check_hpa_regions(uint64_t vva_start, uint64_t size) +{ + uint32_t i, nregions = 0, page_size = getpagesize(); + uint64_t cur_phys_addr = 0, next_phys_addr = 0; + if (vva_start % page_size) { + LOG_DEBUG(VHOST_CONFIG, + "in check_countinous: vva start(%p) mod page_size(%d) " + "has remainder\n", + (void *)(uintptr_t)vva_start, page_size); + return 0; + } + if (size % page_size) { + LOG_DEBUG(VHOST_CONFIG, + "in check_countinous: " + "size((%"PRIu64")) mod page_size(%d) has remainder\n", + size, page_size); + return 0; + } + for (i = 0; i < size - page_size; i = i + page_size) { + cur_phys_addr + = rte_mem_virt2phy((void *)(uintptr_t)(vva_start + i)); + next_phys_addr = rte_mem_virt2phy( + (void *)(uintptr_t)(vva_start + i + page_size)); + if ((cur_phys_addr + page_size) != next_phys_addr) { + ++nregions; + LOG_DEBUG(VHOST_CONFIG, + "in check_continuous: hva addr:(%p) is not " + "continuous with hva addr:(%p), diff:%d\n", + (void *)(uintptr_t)(vva_start + (uint64_t)i), + (void *)(uintptr_t)(vva_start + (uint64_t)i + + page_size), page_size); + LOG_DEBUG(VHOST_CONFIG, + "in check_continuous: hpa addr:(%p) is not " + "continuous with hpa addr:(%p), " + "diff:(%"PRIu64")\n", + (void *)(uintptr_t)cur_phys_addr, + (void *)(uintptr_t)next_phys_addr, + (next_phys_addr-cur_phys_addr)); + } + } + return nregions; +} + +/* + * Divide each region whose vhost virtual address is continous into a few + * sub-regions, make sure the physical address within each sub-region are + * continous. And fill offset(to GPA) and size etc. information of each + * sub-region into regions_hpa. + */ +static uint32_t +fill_hpa_memory_regions(struct virtio_memory_regions_hpa *mem_region_hpa, struct virtio_memory *virtio_memory) +{ + uint32_t regionidx, regionidx_hpa = 0, i, k, page_size = getpagesize(); + uint64_t cur_phys_addr = 0, next_phys_addr = 0, vva_start; + + if (mem_region_hpa == NULL) + return 0; + + for (regionidx = 0; regionidx < virtio_memory->nregions; regionidx++) { + vva_start = virtio_memory->regions[regionidx].guest_phys_address + + virtio_memory->regions[regionidx].address_offset; + mem_region_hpa[regionidx_hpa].guest_phys_address + = virtio_memory->regions[regionidx].guest_phys_address; + mem_region_hpa[regionidx_hpa].host_phys_addr_offset = + rte_mem_virt2phy((void *)(uintptr_t)(vva_start)) - + mem_region_hpa[regionidx_hpa].guest_phys_address; + LOG_DEBUG(VHOST_CONFIG, + "in fill_hpa_regions: guest phys addr start[%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].guest_phys_address)); + LOG_DEBUG(VHOST_CONFIG, + "in fill_hpa_regions: host phys addr start[%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].host_phys_addr_offset)); + for (i = 0, k = 0; + i < virtio_memory->regions[regionidx].memory_size - + page_size; + i += page_size) { + cur_phys_addr = rte_mem_virt2phy( + (void *)(uintptr_t)(vva_start + i)); + next_phys_addr = rte_mem_virt2phy( + (void *)(uintptr_t)(vva_start + + i + page_size)); + if ((cur_phys_addr + page_size) != next_phys_addr) { + mem_region_hpa[regionidx_hpa].guest_phys_address_end = + mem_region_hpa[regionidx_hpa].guest_phys_address + + k + page_size; + mem_region_hpa[regionidx_hpa].memory_size + = k + page_size; + LOG_DEBUG(VHOST_CONFIG, "in fill_hpa_regions: guest " + "phys addr end [%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].guest_phys_address_end)); + LOG_DEBUG(VHOST_CONFIG, + "in fill_hpa_regions: guest phys addr " + "size [%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].memory_size)); + mem_region_hpa[regionidx_hpa + 1].guest_phys_address + = mem_region_hpa[regionidx_hpa].guest_phys_address_end; + ++regionidx_hpa; + mem_region_hpa[regionidx_hpa].host_phys_addr_offset = + next_phys_addr - + mem_region_hpa[regionidx_hpa].guest_phys_address; + LOG_DEBUG(VHOST_CONFIG, "in fill_hpa_regions: guest" + " phys addr start[%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].guest_phys_address)); + LOG_DEBUG(VHOST_CONFIG, + "in fill_hpa_regions: host phys addr " + "start[%d]:(%p)\n", + regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].host_phys_addr_offset)); + k = 0; + } else { + k += page_size; + } + } + mem_region_hpa[regionidx_hpa].guest_phys_address_end + = mem_region_hpa[regionidx_hpa].guest_phys_address + + k + page_size; + mem_region_hpa[regionidx_hpa].memory_size = k + page_size; + LOG_DEBUG(VHOST_CONFIG, "in fill_hpa_regions: guest phys addr end " + "[%d]:(%p)\n", regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].guest_phys_address_end)); + LOG_DEBUG(VHOST_CONFIG, "in fill_hpa_regions: guest phys addr size " + "[%d]:(%p)\n", regionidx_hpa, + (void *)(uintptr_t) + (mem_region_hpa[regionidx_hpa].memory_size)); + ++regionidx_hpa; + } + return regionidx_hpa; } /* @@ -1521,21 +2591,147 @@ 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; + uint32_t regionidx; + + 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; + + if (zero_copy) { + vdev->nregions_hpa = dev->mem->nregions; + for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) { + vdev->nregions_hpa + += check_hpa_regions( + dev->mem->regions[regionidx].guest_phys_address + + dev->mem->regions[regionidx].address_offset, + dev->mem->regions[regionidx].memory_size); + + } + + vdev->regions_hpa = rte_calloc("vhost hpa region", + vdev->nregions_hpa, + sizeof(struct virtio_memory_regions_hpa), + RTE_CACHE_LINE_SIZE); + if (vdev->regions_hpa == NULL) { + RTE_LOG(ERR, VHOST_CONFIG, "Cannot allocate memory for hpa region\n"); + rte_free(vdev); + return -1; + } + + + if (fill_hpa_memory_regions( + vdev->regions_hpa, dev->mem + ) != vdev->nregions_hpa) { + + RTE_LOG(ERR, VHOST_CONFIG, + "hpa memory regions number mismatch: " + "[%d]\n", vdev->nregions_hpa); + rte_free(vdev->regions_hpa); + rte_free(vdev); + return -1; + } + } + /* Add device to main ll */ ll_dev = get_data_ll_free_entry(&ll_root_free); if (ll_dev == NULL) { - RTE_LOG(INFO, DATA, "(%"PRIu64") No free entry found in linked list. Device limit " + 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->dev = dev; + ll_dev->vdev = vdev; add_data_ll_entry(&ll_root_used, ll_dev); + vdev->vmdq_rx_q + = dev->device_fh * queues_per_pool + vmdq_queue_base; + + if (zero_copy) { + uint32_t index = vdev->vmdq_rx_q; + uint32_t count_in_ring, i; + struct mbuf_table *tx_q; + + count_in_ring = rte_ring_count(vpool_array[index].ring); + + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") in new_device: mbuf count in mempool " + "before attach is: %d\n", + dev->device_fh, + rte_mempool_count(vpool_array[index].pool)); + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") in new_device: mbuf count in ring " + "before attach is : %d\n", + dev->device_fh, count_in_ring); + + /* + * Attach all mbufs in vpool.ring and put back intovpool.pool. + */ + for (i = 0; i < count_in_ring; i++) + attach_rxmbuf_zcp(dev); + + LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in " + "mempool after attach is: %d\n", + dev->device_fh, + rte_mempool_count(vpool_array[index].pool)); + LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in " + "ring after attach is : %d\n", + dev->device_fh, + rte_ring_count(vpool_array[index].ring)); + + tx_q = &tx_queue_zcp[(uint16_t)vdev->vmdq_rx_q]; + tx_q->txq_id = vdev->vmdq_rx_q; + + if (rte_eth_dev_tx_queue_start(ports[0], vdev->vmdq_rx_q) != 0) { + struct vpool *vpool = &vpool_array[vdev->vmdq_rx_q]; + + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") In new_device: Failed to start " + "tx queue:%d\n", + dev->device_fh, vdev->vmdq_rx_q); + + mbuf_destroy_zcp(vpool); + rte_free(vdev->regions_hpa); + rte_free(vdev); + return -1; + } + + if (rte_eth_dev_rx_queue_start(ports[0], vdev->vmdq_rx_q) != 0) { + struct vpool *vpool = &vpool_array[vdev->vmdq_rx_q]; + + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") In new_device: Failed to start " + "rx queue:%d\n", + dev->device_fh, vdev->vmdq_rx_q); + + /* Stop the TX queue. */ + if (rte_eth_dev_tx_queue_stop(ports[0], + vdev->vmdq_rx_q) != 0) { + LOG_DEBUG(VHOST_CONFIG, + "(%"PRIu64") In new_device: Failed to " + "stop tx queue:%d\n", + dev->device_fh, vdev->vmdq_rx_q); + } + + mbuf_destroy_zcp(vpool); + rte_free(vdev->regions_hpa); + rte_free(vdev); + return -1; + } + + } /*reset ready flag*/ - dev->ready = DEVICE_MAC_LEARNING; - dev->remove = 0; + vdev->ready = DEVICE_MAC_LEARNING; + vdev->remove = 0; /* Find a suitable lcore to add the device. */ RTE_LCORE_FOREACH_SLAVE(lcore) { @@ -1545,25 +2741,30 @@ new_device (struct virtio_net *dev) } } /* Add device to lcore ll */ - ll_dev->dev->coreid = core_add; - ll_dev = get_data_ll_free_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_free); + ll_dev = get_data_ll_free_entry(&lcore_info[core_add].lcore_ll->ll_root_free); if (ll_dev == NULL) { - RTE_LOG(INFO, DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh); + 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); + rte_free(vdev->regions_hpa); + rte_free(vdev); return -1; } - ll_dev->dev = dev; - add_data_ll_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_used, ll_dev); + 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. */ - set_irq_status(dev); - lcore_info[ll_dev->dev->coreid].lcore_ll->device_num++; + 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, DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, dev->coreid); + RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, vdev->coreid); return 0; } @@ -1602,12 +2803,19 @@ print_stats(void) dev_ll = ll_root_used; while (dev_ll != NULL) { - device_fh = (uint32_t)dev_ll->dev->device_fh; + 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); - rx = rte_atomic64_read(&dev_statistics[device_fh].rx); + if (zero_copy == 0) { + rx_total = rte_atomic64_read( + &dev_statistics[device_fh].rx_total_atomic); + rx = rte_atomic64_read( + &dev_statistics[device_fh].rx_atomic); + } else { + rx_total = dev_statistics[device_fh].rx_total; + rx = dev_statistics[device_fh].rx; + } rx_dropped = rx_total - rx; printf("\nStatistics for device %"PRIu32" ------------------------------" @@ -1631,18 +2839,52 @@ print_stats(void) } } +static void +setup_mempool_tbl(int socket, uint32_t index, char *pool_name, + char *ring_name, uint32_t nb_mbuf) +{ + vpool_array[index].pool = rte_pktmbuf_pool_create(pool_name, nb_mbuf, + MBUF_CACHE_SIZE_ZCP, 0, MBUF_DATA_SIZE_ZCP, socket); + if (vpool_array[index].pool != NULL) { + vpool_array[index].ring + = rte_ring_create(ring_name, + rte_align32pow2(nb_mbuf + 1), + socket, RING_F_SP_ENQ | RING_F_SC_DEQ); + if (likely(vpool_array[index].ring != NULL)) { + LOG_DEBUG(VHOST_CONFIG, + "in setup_mempool_tbl: mbuf count in " + "mempool is: %d\n", + rte_mempool_count(vpool_array[index].pool)); + LOG_DEBUG(VHOST_CONFIG, + "in setup_mempool_tbl: mbuf count in " + "ring is: %d\n", + rte_ring_count(vpool_array[index].ring)); + } else { + rte_exit(EXIT_FAILURE, "ring_create(%s) failed", + ring_name); + } + + /* Need consider head room. */ + vpool_array[index].buf_size = VIRTIO_DESCRIPTOR_LEN_ZCP; + } else { + rte_exit(EXIT_FAILURE, "mempool_create(%s) failed", pool_name); + } +} + + /* * 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[]) +main(int argc, char *argv[]) { - struct rte_mempool *mbuf_pool; + 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 */ @@ -1657,9 +2899,6 @@ MAIN(int argc, char *argv[]) if (ret < 0) rte_exit(EXIT_FAILURE, "Invalid argument\n"); - if (rte_pmd_init_all() != 0 || rte_eal_pci_probe() != 0) - rte_exit(EXIT_FAILURE, "Error with NIC driver initialization\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; @@ -1676,27 +2915,73 @@ MAIN(int argc, char *argv[]) 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 - */ + * 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, PORT, "Current enabled port number is %u," + 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"); + if (zero_copy == 0) { + /* Create the mbuf pool. */ + mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL", + NUM_MBUFS_PER_PORT * valid_num_ports, MBUF_CACHE_SIZE, + 0, MBUF_DATA_SIZE, rte_socket_id()); + 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; + + if (vm2vm_mode == VM2VM_HARDWARE) { + /* Enable VT loop back to let L2 switch to do it. */ + vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1; + LOG_DEBUG(VHOST_CONFIG, + "Enable loop back for L2 switch in vmdq.\n"); + } + } else { + uint32_t nb_mbuf; + char pool_name[RTE_MEMPOOL_NAMESIZE]; + char ring_name[RTE_MEMPOOL_NAMESIZE]; + + nb_mbuf = num_rx_descriptor + + num_switching_cores * MBUF_CACHE_SIZE_ZCP + + num_switching_cores * MAX_PKT_BURST; + + for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) { + snprintf(pool_name, sizeof(pool_name), + "rxmbuf_pool_%u", queue_id); + snprintf(ring_name, sizeof(ring_name), + "rxmbuf_ring_%u", queue_id); + setup_mempool_tbl(rte_socket_id(), queue_id, + pool_name, ring_name, nb_mbuf); + } + + nb_mbuf = num_tx_descriptor + + num_switching_cores * MBUF_CACHE_SIZE_ZCP + + num_switching_cores * MAX_PKT_BURST; + + for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) { + snprintf(pool_name, sizeof(pool_name), + "txmbuf_pool_%u", queue_id); + snprintf(ring_name, sizeof(ring_name), + "txmbuf_ring_%u", queue_id); + setup_mempool_tbl(rte_socket_id(), + (queue_id + MAX_QUEUES), + pool_name, ring_name, nb_mbuf); + } + if (vm2vm_mode == VM2VM_HARDWARE) { + /* Enable VT loop back to let L2 switch to do it. */ + vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1; + LOG_DEBUG(VHOST_CONFIG, + "Enable loop back for L2 switch in vmdq.\n"); + } + } /* Set log level. */ rte_set_log_level(LOG_LEVEL); @@ -1704,11 +2989,13 @@ MAIN(int argc, char *argv[]) for (portid = 0; portid < nb_ports; portid++) { /* skip ports that are not enabled */ if ((enabled_port_mask & (1 << portid)) == 0) { - RTE_LOG(INFO, PORT, "Skipping disabled port %d\n", portid); + RTE_LOG(INFO, VHOST_PORT, + "Skipping disabled port %d\n", portid); continue; } - if (port_init(portid, mbuf_pool) != 0) - rte_exit(EXIT_FAILURE, "Cannot initialize network ports\n"); + if (port_init(portid) != 0) + rte_exit(EXIT_FAILURE, + "Cannot initialize network ports\n"); } /* Initialise all linked lists. */ @@ -1723,19 +3010,56 @@ MAIN(int argc, char *argv[]) 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); + if (zero_copy == 0) { + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + rte_eal_remote_launch(switch_worker, + mbuf_pool, lcore_id); + } + } else { + uint32_t count_in_mempool, index, i; + for (index = 0; index < 2*MAX_QUEUES; index++) { + /* For all RX and TX queues. */ + count_in_mempool + = rte_mempool_count(vpool_array[index].pool); + + /* + * Transfer all un-attached mbufs from vpool.pool + * to vpoo.ring. + */ + for (i = 0; i < count_in_mempool; i++) { + struct rte_mbuf *mbuf + = __rte_mbuf_raw_alloc( + vpool_array[index].pool); + rte_ring_sp_enqueue(vpool_array[index].ring, + (void *)mbuf); + } + + LOG_DEBUG(VHOST_CONFIG, + "in main: mbuf count in mempool at initial " + "is: %d\n", count_in_mempool); + LOG_DEBUG(VHOST_CONFIG, + "in main: mbuf count in ring at initial is :" + " %d\n", + rte_ring_count(vpool_array[index].ring)); + } + + RTE_LCORE_FOREACH_SLAVE(lcore_id) + rte_eal_remote_launch(switch_worker_zcp, NULL, + lcore_id); } + if (mergeable == 0) + rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF); + /* Register CUSE device to handle IOCTLs. */ - ret = register_cuse_device((char*)&dev_basename, dev_index, get_virtio_net_callbacks()); + ret = rte_vhost_driver_register((char *)&dev_basename); if (ret != 0) rte_exit(EXIT_FAILURE,"CUSE device setup failure.\n"); - init_virtio_net(&virtio_net_device_ops); + rte_vhost_driver_callback_register(&virtio_net_device_ops); /* Start CUSE session. */ - start_cuse_session_loop(); + rte_vhost_driver_session_start(); return 0; }