-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2017 Intel Corporation
*/
#include <arpa/inet.h>
#include <sys/param.h>
#include <unistd.h>
-#include <rte_atomic.h>
#include <rte_cycles.h>
#include <rte_ethdev.h>
#include <rte_log.h>
#include <rte_string_fns.h>
#include <rte_malloc.h>
-#include <rte_virtio_net.h>
+#include <rte_net.h>
+#include <rte_vhost.h>
#include <rte_ip.h>
#include <rte_tcp.h>
-#include <rte_udp.h>
-#include <rte_sctp.h>
+#include <rte_pause.h>
+#include "ioat.h"
#include "main.h"
#ifndef MAX_QUEUES
/* the maximum number of external ports supported */
#define MAX_SUP_PORTS 1
-/*
- * Calculate the number of buffers needed per port
- */
-#define NUM_MBUFS_PER_PORT ((MAX_QUEUES*RTE_TEST_RX_DESC_DEFAULT) + \
- (num_switching_cores*MAX_PKT_BURST) + \
- (num_switching_cores*RTE_TEST_TX_DESC_DEFAULT) +\
- (num_switching_cores*MBUF_CACHE_SIZE))
-
#define MBUF_CACHE_SIZE 128
#define MBUF_DATA_SIZE RTE_MBUF_DEFAULT_BUF_SIZE
-/*
- * 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 VIRTIO_DESCRIPTOR_LEN_ZCP RTE_MBUF_DEFAULT_DATAROOM
-#define MBUF_DATA_SIZE_ZCP RTE_MBUF_DEFAULT_BUF_SIZE
-#define MBUF_CACHE_SIZE_ZCP 0
-
-#define MAX_PKT_BURST 32 /* Max burst size for RX/TX */
#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 DEVICE_RX 1
#define DEVICE_SAFE_REMOVE 2
-/* Config_core_flag status definitions. */
-#define REQUEST_DEV_REMOVAL 1
-#define ACK_DEV_REMOVAL 0
-
/* Configurable number of RX/TX ring descriptors */
#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 snprintfs. */
-#define MAX_PRINT_BUFF 6072
-
-/* Maximum character device basename size. */
-#define MAX_BASENAME_SZ 10
-
-/* Maximum long option length for option parsing. */
-#define MAX_LONG_OPT_SZ 64
-
-/* Used to compare MAC addresses. */
-#define MAC_ADDR_CMP 0xFFFFFFFFFFFFULL
-
-/* Number of descriptors per cacheline. */
-#define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc))
-
-#define MBUF_EXT_MEM(mb) (rte_mbuf_from_indirect(mb) != (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;
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 struct rte_mempool *mbuf_pool;
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. */
typedef enum {
VM2VM_DISABLED = 0,
} 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. */
/* Disable TSO offload */
static uint32_t enable_tso;
+static int client_mode;
+
+static int builtin_net_driver;
+
+static int async_vhost_driver;
+
+static char *dma_type;
+
/* Specify timeout (in useconds) between retries on RX. */
static uint32_t burst_rx_delay_time = BURST_RX_WAIT_US;
/* Specify the number of retries on RX. */
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";
+/* Socket file paths. Can be set by user */
+static char *socket_files;
+static int nb_sockets;
/* empty vmdq configuration structure. Filled in programatically */
static struct rte_eth_conf vmdq_conf_default = {
.rxmode = {
.mq_mode = ETH_MQ_RX_VMDQ_ONLY,
.split_hdr_size = 0,
- .header_split = 0, /**< Header Split disabled */
- .hw_ip_checksum = 0, /**< IP checksum offload disabled */
- .hw_vlan_filter = 0, /**< VLAN filtering disabled */
/*
- * It is necessary for 1G NIC such as I350,
+ * VLAN strip is necessary for 1G NIC such as I350,
* this fixes bug of ipv4 forwarding in guest can't
* forward pakets from one virtio dev to another virtio dev.
*/
- .hw_vlan_strip = 1, /**< VLAN strip enabled. */
- .jumbo_frame = 0, /**< Jumbo Frame Support disabled */
- .hw_strip_crc = 0, /**< CRC stripped by hardware */
+ .offloads = DEV_RX_OFFLOAD_VLAN_STRIP,
},
.txmode = {
.mq_mode = ETH_MQ_TX_NONE,
+ .offloads = (DEV_TX_OFFLOAD_IPV4_CKSUM |
+ DEV_TX_OFFLOAD_TCP_CKSUM |
+ DEV_TX_OFFLOAD_VLAN_INSERT |
+ DEV_TX_OFFLOAD_MULTI_SEGS |
+ DEV_TX_OFFLOAD_TCP_TSO),
},
.rx_adv_conf = {
/*
},
};
+
static unsigned lcore_ids[RTE_MAX_LCORE];
-static uint8_t ports[RTE_MAX_ETHPORTS];
+static uint16_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,
};
/* ethernet addresses of ports */
-static struct ether_addr vmdq_ports_eth_addr[RTE_MAX_ETHPORTS];
+static struct rte_ether_addr vmdq_ports_eth_addr[RTE_MAX_ETHPORTS];
-/* heads for the main used and free linked lists for the data path. */
-static struct virtio_net_data_ll *ll_root_used = NULL;
-static struct virtio_net_data_ll *ll_root_free = NULL;
+static struct vhost_dev_tailq_list vhost_dev_list =
+ TAILQ_HEAD_INITIALIZER(vhost_dev_list);
-/* Array of data core structures containing information on individual core linked lists. */
static struct lcore_info lcore_info[RTE_MAX_LCORE];
/* Used for queueing bursts of TX packets. */
struct rte_mbuf *m_table[MAX_PKT_BURST];
};
+struct vhost_bufftable {
+ uint32_t len;
+ uint64_t pre_tsc;
+ struct rte_mbuf *m_table[MAX_PKT_BURST];
+};
+
/* 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];
- unsigned char h_source[ETH_ALEN];
- __be16 h_vlan_proto;
- __be16 h_vlan_TCI;
- __be16 h_vlan_encapsulated_proto;
-};
+/*
+ * Vhost TX buffer for each data core.
+ * Every data core maintains a TX buffer for every vhost device,
+ * which is used for batch pkts enqueue for higher performance.
+ */
+struct vhost_bufftable *vhost_txbuff[RTE_MAX_LCORE * MAX_VHOST_DEVICE];
-/* Header lengths. */
+#define MBUF_TABLE_DRAIN_TSC ((rte_get_tsc_hz() + US_PER_S - 1) \
+ / US_PER_S * BURST_TX_DRAIN_US)
#define VLAN_HLEN 4
-#define VLAN_ETH_HLEN 18
-
-/* Per-device statistics struct */
-struct device_statistics {
- uint64_t tx_total;
- rte_atomic64_t rx_total_atomic;
- uint64_t rx_total;
- uint64_t tx;
- rte_atomic64_t rx_atomic;
- uint64_t rx;
-} __rte_cache_aligned;
-struct device_statistics dev_statistics[MAX_DEVICES];
+
+static inline int
+open_dma(const char *value)
+{
+ if (dma_type != NULL && strncmp(dma_type, "ioat", 4) == 0)
+ return open_ioat(value);
+
+ return -1;
+}
/*
* Builds up the correct configuration for VMDQ VLAN pool map
return 0;
}
-/*
- * 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, VHOST_PORT, "invalid number of devices\n");
- return -1;
- }
- return 0;
-}
-
/*
* Initialises a given port using global settings and with the rx buffers
* coming from the mbuf_pool passed as parameter
*/
static inline int
-port_init(uint8_t port)
+port_init(uint16_t port)
{
struct rte_eth_dev_info dev_info;
struct rte_eth_conf port_conf;
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);
+ retval = rte_eth_dev_info_get(port, &dev_info);
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Error during getting device (port %u) info: %s\n",
+ port, strerror(-retval));
- 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__);
+ return retval;
}
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;
- 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();
- }
+ rx_ring_size = RTE_TEST_RX_DESC_DEFAULT;
+ tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
- retval = validate_num_devices(MAX_DEVICES);
- if (retval < 0)
- return retval;
+ tx_rings = (uint16_t)rte_lcore_count();
/* Get port configuration. */
retval = get_eth_conf(&port_conf, num_devices);
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;
-
- if (enable_tx_csum == 0)
- rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_CSUM);
-
- if (enable_tso == 0) {
- rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4);
- rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO6);
- }
+ if (!rte_eth_dev_is_valid_port(port))
+ return -1;
rx_rings = (uint16_t)dev_info.max_rx_queues;
+ if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
+ port_conf.txmode.offloads |=
+ DEV_TX_OFFLOAD_MBUF_FAST_FREE;
/* Configure ethernet device. */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
- if (retval != 0)
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT, "Failed to configure port %u: %s.\n",
+ port, strerror(-retval));
+ return retval;
+ }
+
+ retval = rte_eth_dev_adjust_nb_rx_tx_desc(port, &rx_ring_size,
+ &tx_ring_size);
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT, "Failed to adjust number of descriptors "
+ "for port %u: %s.\n", port, strerror(-retval));
return retval;
+ }
+ if (rx_ring_size > RTE_TEST_RX_DESC_DEFAULT) {
+ RTE_LOG(ERR, VHOST_PORT, "Mbuf pool has an insufficient size "
+ "for Rx queues on port %u.\n", port);
+ return -1;
+ }
/* Setup the queues. */
+ rxconf->offloads = port_conf.rxmode.offloads;
for (q = 0; q < rx_rings; q ++) {
retval = rte_eth_rx_queue_setup(port, q, rx_ring_size,
rte_eth_dev_socket_id(port),
rxconf,
- vpool_array[q].pool);
- if (retval < 0)
+ mbuf_pool);
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to setup rx queue %u of port %u: %s.\n",
+ q, port, strerror(-retval));
return retval;
+ }
}
+ txconf->offloads = port_conf.txmode.offloads;
for (q = 0; q < tx_rings; q ++) {
retval = rte_eth_tx_queue_setup(port, q, tx_ring_size,
rte_eth_dev_socket_id(port),
txconf);
- if (retval < 0)
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to setup tx queue %u of port %u: %s.\n",
+ q, port, strerror(-retval));
return retval;
+ }
}
/* Start the device. */
retval = rte_eth_dev_start(port);
if (retval < 0) {
- RTE_LOG(ERR, VHOST_DATA, "Failed to start the device.\n");
+ RTE_LOG(ERR, VHOST_PORT, "Failed to start port %u: %s\n",
+ port, strerror(-retval));
return retval;
}
- if (promiscuous)
- rte_eth_promiscuous_enable(port);
+ if (promiscuous) {
+ retval = rte_eth_promiscuous_enable(port);
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to enable promiscuous mode on port %u: %s\n",
+ port, rte_strerror(-retval));
+ return retval;
+ }
+ }
+
+ retval = rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to get MAC address on port %u: %s\n",
+ port, rte_strerror(-retval));
+ return retval;
+ }
- rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
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],
- vmdq_ports_eth_addr[port].addr_bytes[1],
- vmdq_ports_eth_addr[port].addr_bytes[2],
- vmdq_ports_eth_addr[port].addr_bytes[3],
- vmdq_ports_eth_addr[port].addr_bytes[4],
- vmdq_ports_eth_addr[port].addr_bytes[5]);
+ " %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
+ port, RTE_ETHER_ADDR_BYTES(&vmdq_ports_eth_addr[port]));
return 0;
}
/*
- * Set character device basename.
+ * Set socket file path.
*/
static int
-us_vhost_parse_basename(const char *q_arg)
+us_vhost_parse_socket_path(const char *q_arg)
{
+ char *old;
+
/* parse number string */
+ if (strnlen(q_arg, PATH_MAX) == PATH_MAX)
+ return -1;
- if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ)
+ old = socket_files;
+ socket_files = realloc(socket_files, PATH_MAX * (nb_sockets + 1));
+ if (socket_files == NULL) {
+ free(old);
return -1;
- else
- snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);
+ }
+
+ strlcpy(socket_files + nb_sockets * PATH_MAX, q_arg, PATH_MAX);
+ nb_sockets++;
return 0;
}
/* parse hexadecimal string */
pm = strtoul(portmask, &end, 16);
if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0') || (errno != 0))
- return -1;
-
- if (pm == 0)
- return -1;
+ return 0;
return pm;
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 <name>\n"
+ " --socket-file <path>\n"
" --nb-devices ND\n"
" -p PORTMASK: Set mask for ports to be used by application\n"
" --vm2vm [0|1|2]: disable/software(default)/hardware vm2vm comms\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"
- " --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"
+ " --socket-file: The path of the socket file.\n"
" --tx-csum [0|1] disable/enable TX checksum offload.\n"
- " --tso [0|1] disable/enable TCP segment offload.\n",
+ " --tso [0|1] disable/enable TCP segment offload.\n"
+ " --client register a vhost-user socket as client mode.\n"
+ " --dma-type register dma type for your vhost async driver. For example \"ioat\" for now.\n"
+ " --dmas register dma channel for specific vhost device.\n",
prgname);
}
+enum {
+#define OPT_VM2VM "vm2vm"
+ OPT_VM2VM_NUM = 256,
+#define OPT_RX_RETRY "rx-retry"
+ OPT_RX_RETRY_NUM,
+#define OPT_RX_RETRY_DELAY "rx-retry-delay"
+ OPT_RX_RETRY_DELAY_NUM,
+#define OPT_RX_RETRY_NUMB "rx-retry-num"
+ OPT_RX_RETRY_NUMB_NUM,
+#define OPT_MERGEABLE "mergeable"
+ OPT_MERGEABLE_NUM,
+#define OPT_STATS "stats"
+ OPT_STATS_NUM,
+#define OPT_SOCKET_FILE "socket-file"
+ OPT_SOCKET_FILE_NUM,
+#define OPT_TX_CSUM "tx-csum"
+ OPT_TX_CSUM_NUM,
+#define OPT_TSO "tso"
+ OPT_TSO_NUM,
+#define OPT_CLIENT "client"
+ OPT_CLIENT_NUM,
+#define OPT_BUILTIN_NET_DRIVER "builtin-net-driver"
+ OPT_BUILTIN_NET_DRIVER_NUM,
+#define OPT_DMA_TYPE "dma-type"
+ OPT_DMA_TYPE_NUM,
+#define OPT_DMAS "dmas"
+ OPT_DMAS_NUM,
+};
+
/*
* Parse the arguments given in the command line of the application.
*/
unsigned i;
const char *prgname = argv[0];
static struct option long_option[] = {
- {"vm2vm", required_argument, NULL, 0},
- {"rx-retry", required_argument, NULL, 0},
- {"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},
- {"zero-copy", required_argument, NULL, 0},
- {"rx-desc-num", required_argument, NULL, 0},
- {"tx-desc-num", required_argument, NULL, 0},
- {"tx-csum", required_argument, NULL, 0},
- {"tso", required_argument, NULL, 0},
+ {OPT_VM2VM, required_argument,
+ NULL, OPT_VM2VM_NUM},
+ {OPT_RX_RETRY, required_argument,
+ NULL, OPT_RX_RETRY_NUM},
+ {OPT_RX_RETRY_DELAY, required_argument,
+ NULL, OPT_RX_RETRY_DELAY_NUM},
+ {OPT_RX_RETRY_NUMB, required_argument,
+ NULL, OPT_RX_RETRY_NUMB_NUM},
+ {OPT_MERGEABLE, required_argument,
+ NULL, OPT_MERGEABLE_NUM},
+ {OPT_STATS, required_argument,
+ NULL, OPT_STATS_NUM},
+ {OPT_SOCKET_FILE, required_argument,
+ NULL, OPT_SOCKET_FILE_NUM},
+ {OPT_TX_CSUM, required_argument,
+ NULL, OPT_TX_CSUM_NUM},
+ {OPT_TSO, required_argument,
+ NULL, OPT_TSO_NUM},
+ {OPT_CLIENT, no_argument,
+ NULL, OPT_CLIENT_NUM},
+ {OPT_BUILTIN_NET_DRIVER, no_argument,
+ NULL, OPT_BUILTIN_NET_DRIVER_NUM},
+ {OPT_DMA_TYPE, required_argument,
+ NULL, OPT_DMA_TYPE_NUM},
+ {OPT_DMAS, required_argument,
+ NULL, OPT_DMAS_NUM},
{NULL, 0, 0, 0},
};
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, (VM2VM_LAST - 1));
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG,
- "Invalid argument for "
- "vm2vm [0|1|2]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- vm2vm_mode = (vm2vm_type)ret;
- }
+ case OPT_VM2VM_NUM:
+ ret = parse_num_opt(optarg, (VM2VM_LAST - 1));
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for "
+ "vm2vm [0|1|2]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ vm2vm_mode = (vm2vm_type)ret;
+ break;
- /* Enable/disable retries on RX. */
- 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, VHOST_CONFIG, "Invalid argument for rx-retry [0|1]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- enable_retry = ret;
- }
+ case OPT_RX_RETRY_NUM:
+ ret = parse_num_opt(optarg, 1);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry [0|1]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ enable_retry = ret;
+ break;
- /* Enable/disable TX checksum offload. */
- if (!strncmp(long_option[option_index].name, "tx-csum", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, 1);
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for tx-csum [0|1]\n");
- us_vhost_usage(prgname);
- return -1;
- } else
- enable_tx_csum = ret;
+ case OPT_TX_CSUM_NUM:
+ ret = parse_num_opt(optarg, 1);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for tx-csum [0|1]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ enable_tx_csum = ret;
+ break;
- /* Enable/disable TSO offload. */
- if (!strncmp(long_option[option_index].name, "tso", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, 1);
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for tso [0|1]\n");
- us_vhost_usage(prgname);
- return -1;
- } else
- enable_tso = ret;
+ case OPT_TSO_NUM:
+ ret = parse_num_opt(optarg, 1);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for tso [0|1]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ enable_tso = ret;
+ break;
- /* Specify the retries delay time (in useconds) on RX. */
- 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, VHOST_CONFIG, "Invalid argument for rx-retry-delay [0-N]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- burst_rx_delay_time = ret;
- }
+ case OPT_RX_RETRY_DELAY_NUM:
+ ret = parse_num_opt(optarg, INT32_MAX);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-delay [0-N]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ burst_rx_delay_time = ret;
+ break;
- /* Specify the retries number on RX. */
- 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, VHOST_CONFIG, "Invalid argument for rx-retry-num [0-N]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- burst_rx_retry_num = ret;
- }
+ case OPT_RX_RETRY_NUMB_NUM:
+ ret = parse_num_opt(optarg, INT32_MAX);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-num [0-N]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ burst_rx_retry_num = ret;
+ break;
- /* Enable/disable RX mergeable buffers. */
- if (!strncmp(long_option[option_index].name, "mergeable", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, 1);
- if (ret == -1) {
- 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;
- }
- }
+ case OPT_MERGEABLE_NUM:
+ ret = parse_num_opt(optarg, 1);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for mergeable [0|1]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
-
- /* 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 {
- vlan_strip = !!ret;
- vmdq_conf_default.rxmode.hw_vlan_strip =
- vlan_strip;
- }
+ mergeable = !!ret;
+ if (ret) {
+ vmdq_conf_default.rxmode.offloads |=
+ DEV_RX_OFFLOAD_JUMBO_FRAME;
+ vmdq_conf_default.rxmode.max_rx_pkt_len
+ = JUMBO_FRAME_MAX_SIZE;
}
+ break;
- /* Enable/disable stats. */
- if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, INT32_MAX);
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for stats [0..N]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- enable_stats = ret;
- }
+ case OPT_STATS_NUM:
+ ret = parse_num_opt(optarg, INT32_MAX);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for stats [0..N]\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ enable_stats = ret;
+ break;
- /* 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, VHOST_CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ);
- us_vhost_usage(prgname);
- return -1;
- }
+ /* Set socket file path. */
+ case OPT_SOCKET_FILE_NUM:
+ if (us_vhost_parse_socket_path(optarg) == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for socket name (Max %d characters)\n",
+ PATH_MAX);
+ us_vhost_usage(prgname);
+ return -1;
}
+ break;
- /* 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, VHOST_CONFIG,
- "Invalid argument"
- " for zero-copy [0|1]\n");
- us_vhost_usage(prgname);
- return -1;
- } else
- zero_copy = ret;
- }
+ case OPT_DMA_TYPE_NUM:
+ dma_type = optarg;
+ break;
- /* 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;
- }
+ case OPT_DMAS_NUM:
+ if (open_dma(optarg) == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Wrong DMA args\n");
+ us_vhost_usage(prgname);
+ return -1;
}
+ async_vhost_driver = 1;
+ break;
- /* 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 {
- num_tx_descriptor = ret;
- }
- }
+ case OPT_CLIENT_NUM:
+ client_mode = 1;
+ break;
+ case OPT_BUILTIN_NET_DRIVER_NUM:
+ builtin_net_driver = 1;
break;
- /* Invalid option - print options. */
+ /* Invalid option - print options. */
default:
us_vhost_usage(prgname);
return -1;
for (i = 0; i < RTE_MAX_ETHPORTS; i++) {
if (enabled_port_mask & (1 << i))
- ports[num_ports++] = (uint8_t)i;
+ ports[num_ports++] = i;
}
if ((num_ports == 0) || (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;
}
}
for (portid = 0; portid < num_ports; portid ++) {
- if (ports[portid] >= nb_ports) {
- RTE_LOG(INFO, VHOST_PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n",
- ports[portid], (nb_ports - 1));
+ if (!rte_eth_dev_is_valid_port(ports[portid])) {
+ RTE_LOG(INFO, VHOST_PORT,
+ "\nSpecified port ID(%u) is not valid\n",
+ ports[portid]);
ports[portid] = INVALID_PORT_ID;
valid_num_ports--;
}
return valid_num_ports;
}
-/*
- * Macro to print out packet contents. Wrapped in debug define so that the
- * data path is not effected when debug is disabled.
- */
-#ifdef DEBUG
-#define PRINT_PACKET(device, addr, size, header) do { \
- char *pkt_addr = (char*)(addr); \
- unsigned int index; \
- char packet[MAX_PRINT_BUFF]; \
- \
- if ((header)) \
- snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \
- else \
- snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \
- for (index = 0; index < (size); index++) { \
- snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \
- "%02hhx ", pkt_addr[index]); \
- } \
- snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \
- \
- 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 physical addresses.
- * This is used to convert virtio buffer addresses.
- */
-static inline uint64_t __attribute__((always_inline))
-gpa_to_hpa(struct vhost_dev *vdev, uint64_t guest_pa,
- uint32_t buf_len, hpa_type *addr_type)
+static __rte_always_inline struct vhost_dev *
+find_vhost_dev(struct rte_ether_addr *mac)
{
- struct virtio_memory_regions_hpa *region;
- uint32_t regionidx;
- uint64_t vhost_pa = 0;
-
- *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_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(VHOST_DATA, "(%"PRIu64") GPA %p| HPA %p\n",
- vdev->dev->device_fh, (void *)(uintptr_t)guest_pa,
- (void *)(uintptr_t)vhost_pa);
+ struct vhost_dev *vdev;
- return vhost_pa;
-}
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ if (vdev->ready == DEVICE_RX &&
+ rte_is_same_ether_addr(mac, &vdev->mac_address))
+ return vdev;
+ }
-/*
- * Compares a packet destination MAC address to a device MAC address.
- */
-static inline int __attribute__((always_inline))
-ether_addr_cmp(struct ether_addr *ea, struct ether_addr *eb)
-{
- return ((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0;
+ return NULL;
}
/*
static int
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;
+ struct rte_ether_hdr *pkt_hdr;
int i, ret;
/* Learn MAC address of guest device from packet */
- pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
-
- dev_ll = ll_root_used;
+ pkt_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
- while (dev_ll != NULL) {
- 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;
+ if (find_vhost_dev(&pkt_hdr->src_addr)) {
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%d) device is using a registered MAC!\n",
+ vdev->vid);
+ return -1;
}
- for (i = 0; i < ETHER_ADDR_LEN; i++)
- vdev->mac_address.addr_bytes[i] = pkt_hdr->s_addr.addr_bytes[i];
+ for (i = 0; i < RTE_ETHER_ADDR_LEN; i++)
+ vdev->mac_address.addr_bytes[i] =
+ pkt_hdr->src_addr.addr_bytes[i];
/* vlan_tag currently uses the device_id. */
- vdev->vlan_tag = vlan_tags[dev->device_fh];
+ vdev->vlan_tag = vlan_tags[vdev->vid];
/* Print out VMDQ registration info. */
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
- dev->device_fh,
- 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],
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) mac " RTE_ETHER_ADDR_PRT_FMT " and vlan %d registered\n",
+ vdev->vid, RTE_ETHER_ADDR_BYTES(&vdev->mac_address),
vdev->vlan_tag);
/* Register the MAC address. */
ret = rte_eth_dev_mac_addr_add(ports[0], &vdev->mac_address,
- (uint32_t)dev->device_fh + vmdq_pool_base);
+ (uint32_t)vdev->vid + vmdq_pool_base);
if (ret)
- RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
- dev->device_fh);
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%d) failed to add device MAC address to VMDQ\n",
+ vdev->vid);
- /* Enable stripping of the vlan tag as we handle routing. */
- if (vlan_strip)
- rte_eth_dev_set_vlan_strip_on_queue(ports[0],
- (uint16_t)vdev->vmdq_rx_q, 1);
+ rte_eth_dev_set_vlan_strip_on_queue(ports[0], vdev->vmdq_rx_q, 1);
/* Set device as ready for RX. */
vdev->ready = DEVICE_RX;
}
}
+static inline void
+free_pkts(struct rte_mbuf **pkts, uint16_t n)
+{
+ while (n--)
+ rte_pktmbuf_free(pkts[n]);
+}
+
+static __rte_always_inline void
+complete_async_pkts(struct vhost_dev *vdev)
+{
+ struct rte_mbuf *p_cpl[MAX_PKT_BURST];
+ uint16_t complete_count;
+
+ complete_count = rte_vhost_poll_enqueue_completed(vdev->vid,
+ VIRTIO_RXQ, p_cpl, MAX_PKT_BURST);
+ if (complete_count) {
+ free_pkts(p_cpl, complete_count);
+ __atomic_sub_fetch(&vdev->pkts_inflight, complete_count, __ATOMIC_SEQ_CST);
+ }
+
+}
+
+static __rte_always_inline void
+sync_virtio_xmit(struct vhost_dev *dst_vdev, struct vhost_dev *src_vdev,
+ struct rte_mbuf *m)
+{
+ uint16_t ret;
+
+ if (builtin_net_driver) {
+ ret = vs_enqueue_pkts(dst_vdev, VIRTIO_RXQ, &m, 1);
+ } else {
+ ret = rte_vhost_enqueue_burst(dst_vdev->vid, VIRTIO_RXQ, &m, 1);
+ }
+
+ if (enable_stats) {
+ __atomic_add_fetch(&dst_vdev->stats.rx_total_atomic, 1,
+ __ATOMIC_SEQ_CST);
+ __atomic_add_fetch(&dst_vdev->stats.rx_atomic, ret,
+ __ATOMIC_SEQ_CST);
+ src_vdev->stats.tx_total++;
+ src_vdev->stats.tx += ret;
+ }
+}
+
+static __rte_always_inline void
+drain_vhost(struct vhost_dev *vdev)
+{
+ uint16_t ret;
+ uint32_t buff_idx = rte_lcore_id() * MAX_VHOST_DEVICE + vdev->vid;
+ uint16_t nr_xmit = vhost_txbuff[buff_idx]->len;
+ struct rte_mbuf **m = vhost_txbuff[buff_idx]->m_table;
+
+ if (builtin_net_driver) {
+ ret = vs_enqueue_pkts(vdev, VIRTIO_RXQ, m, nr_xmit);
+ } else if (async_vhost_driver) {
+ uint16_t enqueue_fail = 0;
+
+ complete_async_pkts(vdev);
+ ret = rte_vhost_submit_enqueue_burst(vdev->vid, VIRTIO_RXQ, m, nr_xmit);
+ __atomic_add_fetch(&vdev->pkts_inflight, ret, __ATOMIC_SEQ_CST);
+
+ enqueue_fail = nr_xmit - ret;
+ if (enqueue_fail)
+ free_pkts(&m[ret], nr_xmit - ret);
+ } else {
+ ret = rte_vhost_enqueue_burst(vdev->vid, VIRTIO_RXQ,
+ m, nr_xmit);
+ }
+
+ if (enable_stats) {
+ __atomic_add_fetch(&vdev->stats.rx_total_atomic, nr_xmit,
+ __ATOMIC_SEQ_CST);
+ __atomic_add_fetch(&vdev->stats.rx_atomic, ret,
+ __ATOMIC_SEQ_CST);
+ }
+
+ if (!async_vhost_driver)
+ free_pkts(m, nr_xmit);
+}
+
+static __rte_always_inline void
+drain_vhost_table(void)
+{
+ uint16_t lcore_id = rte_lcore_id();
+ struct vhost_bufftable *vhost_txq;
+ struct vhost_dev *vdev;
+ uint64_t cur_tsc;
+
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ vhost_txq = vhost_txbuff[lcore_id * MAX_VHOST_DEVICE
+ + vdev->vid];
+
+ cur_tsc = rte_rdtsc();
+ if (unlikely(cur_tsc - vhost_txq->pre_tsc
+ > MBUF_TABLE_DRAIN_TSC)) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "Vhost TX queue drained after timeout with burst size %u\n",
+ vhost_txq->len);
+ drain_vhost(vdev);
+ vhost_txq->len = 0;
+ vhost_txq->pre_tsc = cur_tsc;
+ }
+ }
+}
+
/*
* 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 int __attribute__((always_inline))
+static __rte_always_inline int
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 = rte_pktmbuf_mtod(m, struct ether_hdr *);
-
- /*get the used devices list*/
- dev_ll = ll_root_used;
-
- 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->device_fh);
- return 0;
- }
- tdev = dev_ll->vdev->dev;
-
-
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is local\n", tdev->device_fh);
-
- if (unlikely(dev_ll->vdev->remove)) {
- /*drop the packet if the device is marked for removal*/
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", tdev->device_fh);
- } else {
- /*send the packet to the local virtio device*/
- ret = rte_vhost_enqueue_burst(tdev, VIRTIO_RXQ, &m, 1);
- if (enable_stats) {
- 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[dev->device_fh].tx_total++;
- dev_statistics[dev->device_fh].tx += ret;
- }
- }
+ struct rte_ether_hdr *pkt_hdr;
+ struct vhost_dev *dst_vdev;
+ struct vhost_bufftable *vhost_txq;
+ uint16_t lcore_id = rte_lcore_id();
+ pkt_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+
+ dst_vdev = find_vhost_dev(&pkt_hdr->dst_addr);
+ if (!dst_vdev)
+ return -1;
- return 0;
- }
- dev_ll = dev_ll->next;
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
+ return 0;
}
- return -1;
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: MAC address is local\n", dst_vdev->vid);
+
+ if (unlikely(dst_vdev->remove)) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) device is marked for removal\n", dst_vdev->vid);
+ return 0;
+ }
+
+ vhost_txq = vhost_txbuff[lcore_id * MAX_VHOST_DEVICE + dst_vdev->vid];
+ vhost_txq->m_table[vhost_txq->len++] = m;
+
+ if (enable_stats) {
+ vdev->stats.tx_total++;
+ vdev->stats.tx++;
+ }
+
+ if (unlikely(vhost_txq->len == MAX_PKT_BURST)) {
+ drain_vhost(dst_vdev);
+ vhost_txq->len = 0;
+ vhost_txq->pre_tsc = rte_rdtsc();
+ }
+ return 0;
}
/*
* 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,
+static __rte_always_inline int
+find_local_dest(struct vhost_dev *vdev, 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;
- }
+ struct vhost_dev *dst_vdev;
+ struct rte_ether_hdr *pkt_hdr =
+ rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
- /*
- * 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,
- (int)*vlan_tag);
+ dst_vdev = find_vhost_dev(&pkt_hdr->dst_addr);
+ if (!dst_vdev)
+ return 0;
- break;
- }
- dev_ll = dev_ll->next;
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
+ return -1;
}
- return 0;
-}
-static uint16_t
-get_psd_sum(void *l3_hdr, uint64_t ol_flags)
-{
- if (ol_flags & PKT_TX_IPV4)
- return rte_ipv4_phdr_cksum(l3_hdr, ol_flags);
- else /* assume ethertype == ETHER_TYPE_IPv6 */
- return rte_ipv6_phdr_cksum(l3_hdr, ol_flags);
+ /*
+ * 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 = vlan_tags[vdev->vid];
+
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: pkt to local VM device id: (%d), vlan tag: %u.\n",
+ vdev->vid, dst_vdev->vid, *vlan_tag);
+
+ return 0;
}
static void virtio_tx_offload(struct rte_mbuf *m)
{
+ struct rte_net_hdr_lens hdr_lens;
+ struct rte_ipv4_hdr *ipv4_hdr;
+ struct rte_tcp_hdr *tcp_hdr;
+ uint32_t ptype;
void *l3_hdr;
- struct ipv4_hdr *ipv4_hdr = NULL;
- struct tcp_hdr *tcp_hdr = NULL;
- struct udp_hdr *udp_hdr = NULL;
- struct sctp_hdr *sctp_hdr = NULL;
- struct ether_hdr *eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- l3_hdr = (char *)eth_hdr + m->l2_len;
+ ptype = rte_net_get_ptype(m, &hdr_lens, RTE_PTYPE_ALL_MASK);
+ m->l2_len = hdr_lens.l2_len;
+ m->l3_len = hdr_lens.l3_len;
+ m->l4_len = hdr_lens.l4_len;
- if (m->tso_segsz != 0) {
- ipv4_hdr = (struct ipv4_hdr *)l3_hdr;
- tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + m->l3_len);
+ l3_hdr = rte_pktmbuf_mtod_offset(m, void *, m->l2_len);
+ tcp_hdr = rte_pktmbuf_mtod_offset(m, struct rte_tcp_hdr *,
+ m->l2_len + m->l3_len);
+
+ m->ol_flags |= PKT_TX_TCP_SEG;
+ if ((ptype & RTE_PTYPE_L3_MASK) == RTE_PTYPE_L3_IPV4) {
+ m->ol_flags |= PKT_TX_IPV4;
m->ol_flags |= PKT_TX_IP_CKSUM;
+ ipv4_hdr = l3_hdr;
ipv4_hdr->hdr_checksum = 0;
- tcp_hdr->cksum = get_psd_sum(l3_hdr, m->ol_flags);
- return;
+ tcp_hdr->cksum = rte_ipv4_phdr_cksum(l3_hdr, m->ol_flags);
+ } else { /* assume ethertype == RTE_ETHER_TYPE_IPV6 */
+ m->ol_flags |= PKT_TX_IPV6;
+ tcp_hdr->cksum = rte_ipv6_phdr_cksum(l3_hdr, m->ol_flags);
}
+}
- if (m->ol_flags & PKT_TX_L4_MASK) {
- switch (m->ol_flags & PKT_TX_L4_MASK) {
- case PKT_TX_TCP_CKSUM:
- tcp_hdr = (struct tcp_hdr *)
- ((char *)l3_hdr + m->l3_len);
- tcp_hdr->cksum = get_psd_sum(l3_hdr, m->ol_flags);
- break;
- case PKT_TX_UDP_CKSUM:
- udp_hdr = (struct udp_hdr *)
- ((char *)l3_hdr + m->l3_len);
- udp_hdr->dgram_cksum = get_psd_sum(l3_hdr, m->ol_flags);
- break;
- case PKT_TX_SCTP_CKSUM:
- sctp_hdr = (struct sctp_hdr *)
- ((char *)l3_hdr + m->l3_len);
- sctp_hdr->cksum = 0;
- break;
- default:
- break;
- }
- }
+static __rte_always_inline void
+do_drain_mbuf_table(struct mbuf_table *tx_q)
+{
+ uint16_t count;
+
+ count = rte_eth_tx_burst(ports[0], tx_q->txq_id,
+ tx_q->m_table, tx_q->len);
+ if (unlikely(count < tx_q->len))
+ free_pkts(&tx_q->m_table[count], tx_q->len - count);
+
+ tx_q->len = 0;
}
/*
- * This function routes the TX packet to the correct interface. This may be a local device
- * or the physical port.
+ * 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))
+static __rte_always_inline void
virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, uint16_t vlan_tag)
{
struct mbuf_table *tx_q;
- struct rte_mbuf **m_table;
- unsigned len, ret, offset = 0;
+ unsigned offset = 0;
const uint16_t lcore_id = rte_lcore_id();
- struct virtio_net *dev = vdev->dev;
- struct ether_hdr *nh;
+ struct rte_ether_hdr *nh;
+
+
+ nh = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+ if (unlikely(rte_is_broadcast_ether_addr(&nh->dst_addr))) {
+ struct vhost_dev *vdev2;
+
+ TAILQ_FOREACH(vdev2, &vhost_dev_list, global_vdev_entry) {
+ if (vdev2 != vdev)
+ sync_virtio_xmit(vdev2, vdev, m);
+ }
+ goto queue2nic;
+ }
/*check if destination is local VM*/
- if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0)) {
- rte_pktmbuf_free(m);
+ if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0))
return;
- }
if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) {
- if (unlikely(find_local_dest(dev, m, &offset, &vlan_tag) != 0)) {
+ if (unlikely(find_local_dest(vdev, m, &offset,
+ &vlan_tag) != 0)) {
rte_pktmbuf_free(m);
return;
}
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: MAC address is external\n", vdev->vid);
+
+queue2nic:
/*Add packet to the port tx queue*/
tx_q = &lcore_tx_queue[lcore_id];
- len = tx_q->len;
- nh = rte_pktmbuf_mtod(m, struct ether_hdr *);
- if (unlikely(nh->ether_type == rte_cpu_to_be_16(ETHER_TYPE_VLAN))) {
+ nh = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+ if (unlikely(nh->ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_VLAN))) {
/* Guest has inserted the vlan tag. */
- struct vlan_hdr *vh = (struct vlan_hdr *) (nh + 1);
+ struct rte_vlan_hdr *vh = (struct rte_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))
m->vlan_tci = vlan_tag;
}
- if ((m->ol_flags & PKT_TX_L4_MASK) || (m->ol_flags & PKT_TX_TCP_SEG))
+ if (m->ol_flags & PKT_RX_LRO)
virtio_tx_offload(m);
- tx_q->m_table[len] = m;
- len++;
+ tx_q->m_table[tx_q->len++] = m;
if (enable_stats) {
- dev_statistics[dev->device_fh].tx_total++;
- dev_statistics[dev->device_fh].tx++;
+ vdev->stats.tx_total++;
+ vdev->stats.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);
- }
+ if (unlikely(tx_q->len == MAX_PKT_BURST))
+ do_drain_mbuf_table(tx_q);
+}
- len = 0;
- }
- tx_q->len = len;
- return;
-}
-/*
- * This function is called by each data core. It handles all RX/TX registered with the
- * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
- * with all devices in the main linked list.
- */
-static int
-switch_worker(__attribute__((unused)) void *arg)
+static __rte_always_inline void
+drain_mbuf_table(struct mbuf_table *tx_q)
{
- 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;
- 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, i;
- const uint16_t lcore_id = rte_lcore_id();
- const uint16_t num_cores = (uint16_t)rte_lcore_count();
- uint16_t rx_count = 0;
- uint16_t tx_count;
- uint32_t retry = 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;
-
- tx_q = &lcore_tx_queue[lcore_id];
- for (i = 0; i < num_cores; i ++) {
- if (lcore_ids[i] == lcore_id) {
- tx_q->txq_id = i;
- break;
- }
- }
-
- while(1) {
- cur_tsc = rte_rdtsc();
- /*
- * TX burst queue drain
- */
- diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > drain_tsc)) {
-
- if (tx_q->len) {
- LOG_DEBUG(VHOST_DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len);
-
- /*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;
- }
-
- 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;
+ static uint64_t prev_tsc;
+ uint64_t cur_tsc;
- /*
- * Process devices
- */
- dev_ll = lcore_ll->ll_root_used;
-
- while (dev_ll != NULL) {
- /*get virtio device ID*/
- vdev = dev_ll->vdev;
- dev = vdev->dev;
-
- if (unlikely(vdev->remove)) {
- dev_ll = dev_ll->next;
- unlink_vmdq(vdev);
- vdev->ready = DEVICE_SAFE_REMOVE;
- continue;
- }
- if (likely(vdev->ready == DEVICE_RX)) {
- /*Handle guest RX*/
- rx_count = rte_eth_rx_burst(ports[0],
- vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
-
- if (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->vdev->dev->device_fh].rx_total_atomic,
- rx_count);
- rte_atomic64_add(
- &dev_statistics[dev_ll->vdev->dev->device_fh].rx_atomic, ret_count);
- }
- while (likely(rx_count)) {
- rx_count--;
- rte_pktmbuf_free(pkts_burst[rx_count]);
- }
-
- }
- }
+ if (tx_q->len == 0)
+ return;
- 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);
- }
+ cur_tsc = rte_rdtsc();
+ if (unlikely(cur_tsc - prev_tsc > MBUF_TABLE_DRAIN_TSC)) {
+ prev_tsc = cur_tsc;
- /*move to the next device in the list*/
- dev_ll = dev_ll->next;
- }
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "TX queue drained after timeout with burst size %u\n",
+ tx_q->len);
+ do_drain_mbuf_table(tx_q);
}
-
- return 0;
-}
-
-/*
- * 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)
+static __rte_always_inline void
+drain_eth_rx(struct vhost_dev *vdev)
{
- struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ];
- uint16_t avail_idx;
- uint32_t retry = 0;
- uint16_t free_entries;
+ uint16_t rx_count, enqueue_count;
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
- *res_base_idx = vq->last_used_idx_res;
- avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- free_entries = (avail_idx - *res_base_idx);
+ rx_count = rte_eth_rx_burst(ports[0], vdev->vmdq_rx_q,
+ pkts, MAX_PKT_BURST);
- 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 (!rx_count)
+ return;
/*
- * If retry is enabled and the queue is full then we wait
- * and retry to avoid packet loss.
+ * When "enable_retry" is set, here we wait and retry when there
+ * is no enough free slots in the queue to hold @rx_count packets,
+ * to diminish packet loss.
*/
- if (enable_retry && unlikely(count > free_entries)) {
+ if (enable_retry &&
+ unlikely(rx_count > rte_vhost_avail_entries(vdev->vid,
+ VIRTIO_RXQ))) {
+ uint32_t retry;
+
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)
+ if (rx_count <= rte_vhost_avail_entries(vdev->vid,
+ VIRTIO_RXQ))
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(vq->callfd, (eventfd_t)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;
- void *obj = NULL;
- struct rte_mbuf *mbuf;
- 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, &obj);
- mbuf = obj;
- 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, obj);
- 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;
+ if (builtin_net_driver) {
+ enqueue_count = vs_enqueue_pkts(vdev, VIRTIO_RXQ,
+ pkts, rx_count);
+ } else if (async_vhost_driver) {
+ uint16_t enqueue_fail = 0;
- 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);
+ complete_async_pkts(vdev);
+ enqueue_count = rte_vhost_submit_enqueue_burst(vdev->vid,
+ VIRTIO_RXQ, pkts, rx_count);
+ __atomic_add_fetch(&vdev->pkts_inflight, enqueue_count, __ATOMIC_SEQ_CST);
- __rte_mbuf_raw_free(mbuf);
+ enqueue_fail = rx_count - enqueue_count;
+ if (enqueue_fail)
+ free_pkts(&pkts[enqueue_count], enqueue_fail);
- 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(vq->callfd, (eventfd_t)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);
- }
+ } else {
+ enqueue_count = rte_vhost_enqueue_burst(vdev->vid, VIRTIO_RXQ,
+ pkts, rx_count);
}
- 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]]);
- }
+ if (enable_stats) {
+ __atomic_add_fetch(&vdev->stats.rx_total_atomic, rx_count,
+ __ATOMIC_SEQ_CST);
+ __atomic_add_fetch(&vdev->stats.rx_atomic, enqueue_count,
+ __ATOMIC_SEQ_CST);
}
- 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(vq->callfd, (eventfd_t)1);
-
- return count;
+ if (!async_vhost_driver)
+ free_pkts(pkts, rx_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)
+static __rte_always_inline void
+drain_virtio_tx(struct vhost_dev *vdev)
{
- struct mbuf_table *tx_q;
- struct rte_mbuf **m_table;
- void *obj = NULL;
- struct rte_mbuf *mbuf;
- 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, &obj);
- mbuf = obj;
- 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;
- }
- }
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+ uint16_t count;
+ uint16_t i;
- 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);
+ if (builtin_net_driver) {
+ count = vs_dequeue_pkts(vdev, VIRTIO_TXQ, mbuf_pool,
+ pkts, MAX_PKT_BURST);
} 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++;
+ count = rte_vhost_dequeue_burst(vdev->vid, VIRTIO_TXQ,
+ mbuf_pool, pkts, MAX_PKT_BURST);
}
- 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);
+ /* setup VMDq for the first packet */
+ if (unlikely(vdev->ready == DEVICE_MAC_LEARNING) && count) {
+ if (vdev->remove || link_vmdq(vdev, pkts[0]) == -1)
+ free_pkts(pkts, count);
}
- tx_q->len = len;
-
- return;
+ for (i = 0; i < count; ++i)
+ virtio_tx_route(vdev, pkts[i], vlan_tags[vdev->vid]);
}
/*
- * 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.
+ * Main function of vhost-switch. It basically does:
+ *
+ * for each vhost device {
+ * - drain_eth_rx()
+ *
+ * Which drains the host eth Rx queue linked to the vhost device,
+ * and deliver all of them to guest virito Rx ring associated with
+ * this vhost device.
+ *
+ * - drain_virtio_tx()
+ *
+ * Which drains the guest virtio Tx queue and deliver all of them
+ * to the target, which could be another vhost device, or the
+ * physical eth dev. The route is done in function "virtio_tx_route".
+ * }
*/
static int
-switch_worker_zcp(__attribute__((unused)) void *arg)
+switch_worker(void *arg __rte_unused)
{
- 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;
+ unsigned i;
+ unsigned lcore_id = rte_lcore_id();
+ struct vhost_dev *vdev;
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;
+ tx_q = &lcore_tx_queue[lcore_id];
+ for (i = 0; i < rte_lcore_count(); i++) {
+ if (lcore_ids[i] == lcore_id) {
+ tx_q->txq_id = i;
+ break;
}
+ }
- rte_prefetch0(lcore_ll->ll_root_used);
-
+ while(1) {
+ drain_mbuf_table(tx_q);
+ drain_vhost_table();
/*
- * Inform the configuration core that we have exited the linked
- * list and that no devices are in use if requested.
+ * 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;
+ if (lcore_info[lcore_id].dev_removal_flag == REQUEST_DEV_REMOVAL)
+ lcore_info[lcore_id].dev_removal_flag = ACK_DEV_REMOVAL;
- while ((dev_ll != NULL) && (dev_ll->vdev != NULL)) {
- vdev = dev_ll->vdev;
- dev = vdev->dev;
+ /*
+ * Process vhost devices
+ */
+ TAILQ_FOREACH(vdev, &lcore_info[lcore_id].vdev_list,
+ lcore_vdev_entry) {
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->ready == DEVICE_RX))
+ drain_eth_rx(vdev);
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)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- /* Set next as NULL and use a compiler barrier to avoid reordering. */
- ll_dev->next = NULL;
- rte_compiler_barrier();
-
- /* If ll == NULL then this is the first device. */
- if (ll) {
- /* Increment to the tail of the linked list. */
- while ((ll->next != NULL) )
- ll = ll->next;
-
- ll->next = ll_dev;
- } else {
- *ll_root_addr = ll_dev;
- }
-}
-
-/*
- * Remove an entry from a used linked list. The entry must then be added to
- * the free linked list using put_data_ll_free_entry().
- */
-static void
-rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev,
- struct virtio_net_data_ll *ll_dev_last)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- if (unlikely((ll == NULL) || (ll_dev == NULL)))
- return;
-
- if (ll_dev == ll)
- *ll_root_addr = ll_dev->next;
- else
- if (likely(ll_dev_last != NULL))
- ll_dev_last->next = ll_dev->next;
- else
- RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n");
-}
-
-/*
- * Find and return an entry from the free linked list.
- */
-static struct virtio_net_data_ll *
-get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
- struct virtio_net_data_ll *ll_dev;
-
- if (ll_free == NULL)
- return NULL;
-
- ll_dev = ll_free;
- *ll_root_addr = ll_free->next;
-
- return ll_dev;
-}
-
-/*
- * Place an entry back on to the free linked list.
- */
-static void
-put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
-
- if (ll_dev == NULL)
- return;
-
- ll_dev->next = ll_free;
- *ll_root_addr = ll_dev;
-}
-
-/*
- * Creates a linked list of a given size.
- */
-static struct virtio_net_data_ll *
-alloc_data_ll(uint32_t size)
-{
- struct virtio_net_data_ll *ll_new;
- uint32_t i;
-
- /* Malloc and then chain the linked list. */
- ll_new = malloc(size * sizeof(struct virtio_net_data_ll));
- if (ll_new == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for ll_new.\n");
- return NULL;
- }
-
- for (i = 0; i < size - 1; i++) {
- ll_new[i].vdev = NULL;
- ll_new[i].next = &ll_new[i+1];
- }
- ll_new[i].next = NULL;
-
- return ll_new;
-}
-
-/*
- * Create the main linked list along with each individual cores linked list. A used and a free list
- * are created to manage entries.
- */
-static int
-init_data_ll (void)
-{
- int lcore;
-
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info));
- if (lcore_info[lcore].lcore_ll == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n");
- return -1;
+ drain_virtio_tx(vdev);
}
-
- lcore_info[lcore].lcore_ll->device_num = 0;
- lcore_info[lcore].lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
- lcore_info[lcore].lcore_ll->ll_root_used = NULL;
- if (num_devices % num_switching_cores)
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll((num_devices / num_switching_cores) + 1);
- else
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll(num_devices / num_switching_cores);
}
- /* Allocate devices up to a maximum of MAX_DEVICES. */
- ll_root_free = alloc_data_ll(MIN((num_devices), MAX_DEVICES));
-
return 0;
}
/*
- * Remove a device from the specific data core linked list and from the main linked list. Synchonization
- * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
+ * Remove a device from the specific data core linked list and from the
+ * main linked list. Synchonization occurs through the use of the
+ * lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
* of dev->remove=1 which can cause an infinite loop in the rte_pause loop.
*/
static void
-destroy_device (volatile struct virtio_net *dev)
+destroy_device(int vid)
{
- struct virtio_net_data_ll *ll_lcore_dev_cur;
- struct virtio_net_data_ll *ll_main_dev_cur;
- struct virtio_net_data_ll *ll_lcore_dev_last = NULL;
- struct virtio_net_data_ll *ll_main_dev_last = NULL;
- struct vhost_dev *vdev;
+ struct vhost_dev *vdev = NULL;
int lcore;
+ uint16_t i;
- dev->flags &= ~VIRTIO_DEV_RUNNING;
-
- vdev = (struct vhost_dev *)dev->priv;
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ if (vdev->vid == vid)
+ break;
+ }
+ if (!vdev)
+ return;
/*set the remove flag. */
vdev->remove = 1;
while(vdev->ready != DEVICE_SAFE_REMOVE) {
rte_pause();
}
- /* Search for entry to be removed from lcore ll */
- ll_lcore_dev_cur = lcore_info[vdev->coreid].lcore_ll->ll_root_used;
- while (ll_lcore_dev_cur != NULL) {
- if (ll_lcore_dev_cur->vdev == vdev) {
- break;
- } else {
- ll_lcore_dev_last = ll_lcore_dev_cur;
- ll_lcore_dev_cur = ll_lcore_dev_cur->next;
- }
- }
+ for (i = 0; i < RTE_MAX_LCORE; i++)
+ rte_free(vhost_txbuff[i * MAX_VHOST_DEVICE + vid]);
- if (ll_lcore_dev_cur == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG,
- "(%"PRIu64") Failed to find the dev to be destroy.\n",
- dev->device_fh);
- return;
- }
+ if (builtin_net_driver)
+ vs_vhost_net_remove(vdev);
- /* Search for entry to be removed from main ll */
- ll_main_dev_cur = ll_root_used;
- ll_main_dev_last = NULL;
- while (ll_main_dev_cur != NULL) {
- if (ll_main_dev_cur->vdev == vdev) {
- break;
- } else {
- ll_main_dev_last = ll_main_dev_cur;
- ll_main_dev_cur = ll_main_dev_cur->next;
- }
- }
+ TAILQ_REMOVE(&lcore_info[vdev->coreid].vdev_list, vdev,
+ lcore_vdev_entry);
+ TAILQ_REMOVE(&vhost_dev_list, vdev, global_vdev_entry);
- /* Remove entries from the lcore and main ll. */
- rm_data_ll_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_used, ll_lcore_dev_cur, ll_lcore_dev_last);
- rm_data_ll_entry(&ll_root_used, ll_main_dev_cur, ll_main_dev_last);
/* Set the dev_removal_flag on each lcore. */
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- lcore_info[lcore].lcore_ll->dev_removal_flag = REQUEST_DEV_REMOVAL;
- }
+ RTE_LCORE_FOREACH_WORKER(lcore)
+ lcore_info[lcore].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.
+ * Once each core has set the dev_removal_flag to ACK_DEV_REMOVAL
+ * we can be sure that they can no longer access the device removed
+ * from the linked lists and that the devices are no longer in use.
*/
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- while (lcore_info[lcore].lcore_ll->dev_removal_flag != ACK_DEV_REMOVAL) {
+ RTE_LCORE_FOREACH_WORKER(lcore) {
+ while (lcore_info[lcore].dev_removal_flag != ACK_DEV_REMOVAL)
rte_pause();
- }
}
- /* Add the entries back to the lcore and main free ll.*/
- put_data_ll_free_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur);
- put_data_ll_free_entry(&ll_root_free, ll_main_dev_cur);
-
- /* Decrement number of device on the lcore. */
- lcore_info[vdev->coreid].lcore_ll->device_num--;
-
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
+ lcore_info[vdev->coreid].device_num--;
- if (zero_copy) {
- struct vpool *vpool = &vpool_array[vdev->vmdq_rx_q];
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) device has been removed from data core\n",
+ vdev->vid);
- /* 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);
+ if (async_vhost_driver) {
+ uint16_t n_pkt = 0;
+ struct rte_mbuf *m_cpl[vdev->pkts_inflight];
- 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);
+ while (vdev->pkts_inflight) {
+ n_pkt = rte_vhost_clear_queue_thread_unsafe(vid, VIRTIO_RXQ,
+ m_cpl, vdev->pkts_inflight);
+ free_pkts(m_cpl, n_pkt);
+ __atomic_sub_fetch(&vdev->pkts_inflight, n_pkt, __ATOMIC_SEQ_CST);
}
- 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;
+ rte_vhost_async_channel_unregister(vid, VIRTIO_RXQ);
}
- 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;
+ rte_free(vdev);
}
/*
* A new device is added to a data core. First the device is added to the main linked list
- * and the allocated to a specific data core.
+ * and then allocated to a specific data core.
*/
static int
-new_device (struct virtio_net *dev)
+new_device(int vid)
{
- struct virtio_net_data_ll *ll_dev;
int lcore, core_add = 0;
+ uint16_t i;
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);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) couldn't allocate memory for vhost dev\n",
+ vid);
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->vid = vid;
- }
+ for (i = 0; i < RTE_MAX_LCORE; i++) {
+ vhost_txbuff[i * MAX_VHOST_DEVICE + vid]
+ = rte_zmalloc("vhost bufftable",
+ sizeof(struct vhost_bufftable),
+ RTE_CACHE_LINE_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);
+ if (vhost_txbuff[i * MAX_VHOST_DEVICE + vid] == NULL) {
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) couldn't allocate memory for vhost TX\n", vid);
return -1;
}
+ }
+ if (builtin_net_driver)
+ vs_vhost_net_setup(vdev);
- if (fill_hpa_memory_regions(
- vdev->regions_hpa, dev->mem
- ) != vdev->nregions_hpa) {
+ TAILQ_INSERT_TAIL(&vhost_dev_list, vdev, global_vdev_entry);
+ vdev->vmdq_rx_q = vid * queues_per_pool + vmdq_queue_base;
- 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;
+ /*reset ready flag*/
+ vdev->ready = DEVICE_MAC_LEARNING;
+ vdev->remove = 0;
+
+ /* Find a suitable lcore to add the device. */
+ RTE_LCORE_FOREACH_WORKER(lcore) {
+ if (lcore_info[lcore].device_num < device_num_min) {
+ device_num_min = lcore_info[lcore].device_num;
+ core_add = lcore;
}
}
+ vdev->coreid = core_add;
+ TAILQ_INSERT_TAIL(&lcore_info[vdev->coreid].vdev_list, vdev,
+ lcore_vdev_entry);
+ lcore_info[vdev->coreid].device_num++;
- /* Add device to main ll */
- ll_dev = get_data_ll_free_entry(&ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
- "of %d devices per core has been reached\n",
- dev->device_fh, num_devices);
- if (vdev->regions_hpa)
- rte_free(vdev->regions_hpa);
- rte_free(vdev);
- return -1;
- }
- ll_dev->vdev = vdev;
- add_data_ll_entry(&ll_root_used, ll_dev);
- vdev->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);
+ /* Disable notifications. */
+ rte_vhost_enable_guest_notification(vid, VIRTIO_RXQ, 0);
+ rte_vhost_enable_guest_notification(vid, VIRTIO_TXQ, 0);
- /*
- * 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;
- }
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) device has been added to data core %d\n",
+ vid, vdev->coreid);
- 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);
- }
+ if (async_vhost_driver) {
+ struct rte_vhost_async_config config = {0};
+ struct rte_vhost_async_channel_ops channel_ops;
- mbuf_destroy_zcp(vpool);
- rte_free(vdev->regions_hpa);
- rte_free(vdev);
- return -1;
- }
+ if (dma_type != NULL && strncmp(dma_type, "ioat", 4) == 0) {
+ channel_ops.transfer_data = ioat_transfer_data_cb;
+ channel_ops.check_completed_copies =
+ ioat_check_completed_copies_cb;
+ config.features = RTE_VHOST_ASYNC_INORDER;
+
+ return rte_vhost_async_channel_register(vid, VIRTIO_RXQ,
+ config, &channel_ops);
+ }
}
- /*reset ready flag*/
- vdev->ready = DEVICE_MAC_LEARNING;
- vdev->remove = 0;
+ return 0;
+}
- /* Find a suitable lcore to add the device. */
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- if (lcore_info[lcore].lcore_ll->device_num < device_num_min) {
- device_num_min = lcore_info[lcore].lcore_ll->device_num;
- core_add = lcore;
- }
+static int
+vring_state_changed(int vid, uint16_t queue_id, int enable)
+{
+ struct vhost_dev *vdev = NULL;
+
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ if (vdev->vid == vid)
+ break;
}
- /* Add device to lcore ll */
- ll_dev = get_data_ll_free_entry(&lcore_info[core_add].lcore_ll->ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
- vdev->ready = DEVICE_SAFE_REMOVE;
- destroy_device(dev);
- rte_free(vdev->regions_hpa);
- rte_free(vdev);
+ if (!vdev)
return -1;
- }
- ll_dev->vdev = vdev;
- vdev->coreid = core_add;
-
- add_data_ll_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_used, ll_dev);
- /* Initialize device stats */
- memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics));
+ if (queue_id != VIRTIO_RXQ)
+ return 0;
- /* Disable notifications. */
- rte_vhost_enable_guest_notification(dev, VIRTIO_RXQ, 0);
- rte_vhost_enable_guest_notification(dev, VIRTIO_TXQ, 0);
- lcore_info[vdev->coreid].lcore_ll->device_num++;
- dev->flags |= VIRTIO_DEV_RUNNING;
+ if (async_vhost_driver) {
+ if (!enable) {
+ uint16_t n_pkt = 0;
+ struct rte_mbuf *m_cpl[vdev->pkts_inflight];
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, vdev->coreid);
+ while (vdev->pkts_inflight) {
+ n_pkt = rte_vhost_clear_queue_thread_unsafe(vid, queue_id,
+ m_cpl, vdev->pkts_inflight);
+ free_pkts(m_cpl, n_pkt);
+ __atomic_sub_fetch(&vdev->pkts_inflight, n_pkt, __ATOMIC_SEQ_CST);
+ }
+ }
+ }
return 0;
}
* These callback allow devices to be added to the data core when configuration
* has been fully complete.
*/
-static const struct virtio_net_device_ops virtio_net_device_ops =
+static const struct vhost_device_ops virtio_net_device_ops =
{
.new_device = new_device,
.destroy_device = destroy_device,
+ .vring_state_changed = vring_state_changed,
};
/*
* This is a thread will wake up after a period to print stats if the user has
* enabled them.
*/
-static void
-print_stats(void)
+static void *
+print_stats(__rte_unused void *arg)
{
- struct virtio_net_data_ll *dev_ll;
+ struct vhost_dev *vdev;
uint64_t tx_dropped, rx_dropped;
uint64_t tx, tx_total, rx, rx_total;
- uint32_t device_fh;
const char clr[] = { 27, '[', '2', 'J', '\0' };
const char top_left[] = { 27, '[', '1', ';', '1', 'H','\0' };
sleep(enable_stats);
/* Clear screen and move to top left */
- printf("%s%s", clr, top_left);
-
- printf("\nDevice statistics ====================================");
+ printf("%s%s\n", clr, top_left);
+ printf("Device statistics =================================\n");
- dev_ll = ll_root_used;
- while (dev_ll != NULL) {
- device_fh = (uint32_t)dev_ll->vdev->dev->device_fh;
- tx_total = dev_statistics[device_fh].tx_total;
- tx = dev_statistics[device_fh].tx;
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ tx_total = vdev->stats.tx_total;
+ tx = vdev->stats.tx;
tx_dropped = tx_total - tx;
- 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_total = __atomic_load_n(&vdev->stats.rx_total_atomic,
+ __ATOMIC_SEQ_CST);
+ rx = __atomic_load_n(&vdev->stats.rx_atomic,
+ __ATOMIC_SEQ_CST);
rx_dropped = rx_total - rx;
- printf("\nStatistics for device %"PRIu32" ------------------------------"
- "\nTX total: %"PRIu64""
- "\nTX dropped: %"PRIu64""
- "\nTX successful: %"PRIu64""
- "\nRX total: %"PRIu64""
- "\nRX dropped: %"PRIu64""
- "\nRX successful: %"PRIu64"",
- device_fh,
- tx_total,
- tx_dropped,
- tx,
- rx_total,
- rx_dropped,
- rx);
-
- dev_ll = dev_ll->next;
+ printf("Statistics for device %d\n"
+ "-----------------------\n"
+ "TX total: %" PRIu64 "\n"
+ "TX dropped: %" PRIu64 "\n"
+ "TX successful: %" PRIu64 "\n"
+ "RX total: %" PRIu64 "\n"
+ "RX dropped: %" PRIu64 "\n"
+ "RX successful: %" PRIu64 "\n",
+ vdev->vid,
+ tx_total, tx_dropped, tx,
+ rx_total, rx_dropped, rx);
}
- printf("\n======================================================\n");
+
+ printf("===================================================\n");
+
+ fflush(stdout);
}
+
+ return NULL;
}
static void
-setup_mempool_tbl(int socket, uint32_t index, char *pool_name,
- char *ring_name, uint32_t nb_mbuf)
+unregister_drivers(int socket_num)
{
- 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);
- }
+ int i, ret;
- /* Need consider head room. */
- vpool_array[index].buf_size = VIRTIO_DESCRIPTOR_LEN_ZCP;
- } else {
- rte_exit(EXIT_FAILURE, "mempool_create(%s) failed", pool_name);
+ for (i = 0; i < socket_num; i++) {
+ ret = rte_vhost_driver_unregister(socket_files + i * PATH_MAX);
+ if (ret != 0)
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "Fail to unregister vhost driver for %s.\n",
+ socket_files + i * PATH_MAX);
}
}
sigint_handler(__rte_unused int signum)
{
/* Unregister vhost driver. */
- int ret = rte_vhost_driver_unregister((char *)&dev_basename);
- if (ret != 0)
- rte_exit(EXIT_FAILURE, "vhost driver unregister failure.\n");
+ unregister_drivers(nb_sockets);
+
exit(0);
}
/*
- * Main function, does initialisation and calls the per-lcore functions. The CUSE
- * device is also registered here to handle the IOCTLs.
+ * While creating an mbuf pool, one key thing is to figure out how
+ * many mbuf entries is enough for our use. FYI, here are some
+ * guidelines:
+ *
+ * - Each rx queue would reserve @nr_rx_desc mbufs at queue setup stage
+ *
+ * - For each switch core (A CPU core does the packet switch), we need
+ * also make some reservation for receiving the packets from virtio
+ * Tx queue. How many is enough depends on the usage. It's normally
+ * a simple calculation like following:
+ *
+ * MAX_PKT_BURST * max packet size / mbuf size
+ *
+ * So, we definitely need allocate more mbufs when TSO is enabled.
+ *
+ * - Similarly, for each switching core, we should serve @nr_rx_desc
+ * mbufs for receiving the packets from physical NIC device.
+ *
+ * - We also need make sure, for each switch core, we have allocated
+ * enough mbufs to fill up the mbuf cache.
+ */
+static void
+create_mbuf_pool(uint16_t nr_port, uint32_t nr_switch_core, uint32_t mbuf_size,
+ uint32_t nr_queues, uint32_t nr_rx_desc, uint32_t nr_mbuf_cache)
+{
+ uint32_t nr_mbufs;
+ uint32_t nr_mbufs_per_core;
+ uint32_t mtu = 1500;
+
+ if (mergeable)
+ mtu = 9000;
+ if (enable_tso)
+ mtu = 64 * 1024;
+
+ nr_mbufs_per_core = (mtu + mbuf_size) * MAX_PKT_BURST /
+ (mbuf_size - RTE_PKTMBUF_HEADROOM);
+ nr_mbufs_per_core += nr_rx_desc;
+ nr_mbufs_per_core = RTE_MAX(nr_mbufs_per_core, nr_mbuf_cache);
+
+ nr_mbufs = nr_queues * nr_rx_desc;
+ nr_mbufs += nr_mbufs_per_core * nr_switch_core;
+ nr_mbufs *= nr_port;
+
+ mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL", nr_mbufs,
+ nr_mbuf_cache, 0, mbuf_size,
+ rte_socket_id());
+ if (mbuf_pool == NULL)
+ rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
+}
+
+/*
+ * Main function, does initialisation and calls the per-lcore functions.
*/
int
main(int argc, char *argv[])
{
- struct rte_mempool *mbuf_pool = NULL;
unsigned lcore_id, core_id = 0;
unsigned nb_ports, valid_num_ports;
- int ret;
- uint8_t portid;
- uint16_t queue_id;
+ int ret, i;
+ uint16_t portid;
static pthread_t tid;
- char thread_name[RTE_MAX_THREAD_NAME_LEN];
+ uint64_t flags = RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
signal(SIGINT, sigint_handler);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid argument\n");
- for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++)
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+ TAILQ_INIT(&lcore_info[lcore_id].vdev_list);
+
if (rte_lcore_is_enabled(lcore_id))
- lcore_ids[core_id ++] = lcore_id;
+ lcore_ids[core_id++] = lcore_id;
+ }
if (rte_lcore_count() > RTE_MAX_LCORE)
rte_exit(EXIT_FAILURE,"Not enough cores\n");
- /*set the number of swithcing cores available*/
- num_switching_cores = rte_lcore_count()-1;
-
/* Get the number of physical ports. */
- nb_ports = rte_eth_dev_count();
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
+ nb_ports = rte_eth_dev_count_avail();
/*
* Update the global var NUM_PORTS and global array PORTS
return -1;
}
- 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);
- }
+ /*
+ * FIXME: here we are trying to allocate mbufs big enough for
+ * @MAX_QUEUES, but the truth is we're never going to use that
+ * many queues here. We probably should only do allocation for
+ * those queues we are going to use.
+ */
+ create_mbuf_pool(valid_num_ports, rte_lcore_count() - 1, MBUF_DATA_SIZE,
+ MAX_QUEUES, RTE_TEST_RX_DESC_DEFAULT, MBUF_CACHE_SIZE);
- 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");
- }
+ 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;
+ RTE_LOG(DEBUG, VHOST_CONFIG,
+ "Enable loop back for L2 switch in vmdq.\n");
}
- /* Set log level. */
- rte_set_log_level(LOG_LEVEL);
/* initialize all ports */
- for (portid = 0; portid < nb_ports; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
/* skip ports that are not enabled */
if ((enabled_port_mask & (1 << portid)) == 0) {
RTE_LOG(INFO, VHOST_PORT,
"Cannot initialize network ports\n");
}
- /* Initialise all linked lists. */
- if (init_data_ll() == -1)
- rte_exit(EXIT_FAILURE, "Failed to initialize linked list\n");
-
- /* Initialize device stats */
- memset(&dev_statistics, 0, sizeof(dev_statistics));
-
/* Enable stats if the user option is set. */
if (enable_stats) {
- ret = pthread_create(&tid, NULL, (void *)print_stats, NULL);
- if (ret != 0)
+ ret = rte_ctrl_thread_create(&tid, "print-stats", NULL,
+ print_stats, NULL);
+ if (ret < 0)
rte_exit(EXIT_FAILURE,
"Cannot create print-stats thread\n");
-
- /* Set thread_name for aid in debugging. */
- snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "print-stats");
- ret = rte_thread_setname(tid, thread_name);
- if (ret != 0)
- RTE_LOG(ERR, VHOST_CONFIG,
- "Cannot set print-stats name\n");
}
/* Launch all data cores. */
- if (zero_copy == 0) {
- RTE_LCORE_FOREACH_SLAVE(lcore_id) {
- rte_eal_remote_launch(switch_worker,
- mbuf_pool, lcore_id);
+ RTE_LCORE_FOREACH_WORKER(lcore_id)
+ rte_eal_remote_launch(switch_worker, NULL, lcore_id);
+
+ if (client_mode)
+ flags |= RTE_VHOST_USER_CLIENT;
+
+ /* Register vhost user driver to handle vhost messages. */
+ for (i = 0; i < nb_sockets; i++) {
+ char *file = socket_files + i * PATH_MAX;
+
+ if (async_vhost_driver)
+ flags = flags | RTE_VHOST_USER_ASYNC_COPY;
+
+ ret = rte_vhost_driver_register(file, flags);
+ if (ret != 0) {
+ unregister_drivers(i);
+ rte_exit(EXIT_FAILURE,
+ "vhost driver register failure.\n");
}
- } 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));
+ if (builtin_net_driver)
+ rte_vhost_driver_set_features(file, VIRTIO_NET_FEATURES);
+
+ if (mergeable == 0) {
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_MRG_RXBUF);
}
- RTE_LCORE_FOREACH_SLAVE(lcore_id)
- rte_eal_remote_launch(switch_worker_zcp, NULL,
- lcore_id);
- }
+ if (enable_tx_csum == 0) {
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_CSUM);
+ }
- if (mergeable == 0)
- rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF);
+ if (enable_tso == 0) {
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_HOST_TSO4);
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_HOST_TSO6);
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_GUEST_TSO4);
+ rte_vhost_driver_disable_features(file,
+ 1ULL << VIRTIO_NET_F_GUEST_TSO6);
+ }
- /* Register vhost(cuse or user) driver to handle vhost messages. */
- ret = rte_vhost_driver_register((char *)&dev_basename);
- if (ret != 0)
- rte_exit(EXIT_FAILURE, "vhost driver register failure.\n");
+ if (promiscuous) {
+ rte_vhost_driver_enable_features(file,
+ 1ULL << VIRTIO_NET_F_CTRL_RX);
+ }
- rte_vhost_driver_callback_register(&virtio_net_device_ops);
+ ret = rte_vhost_driver_callback_register(file,
+ &virtio_net_device_ops);
+ if (ret != 0) {
+ rte_exit(EXIT_FAILURE,
+ "failed to register vhost driver callbacks.\n");
+ }
- /* Start CUSE session. */
- rte_vhost_driver_session_start();
- return 0;
+ if (rte_vhost_driver_start(file) < 0) {
+ rte_exit(EXIT_FAILURE,
+ "failed to start vhost driver.\n");
+ }
+ }
+ RTE_LCORE_FOREACH_WORKER(lcore_id)
+ rte_eal_wait_lcore(lcore_id);
+
+ /* clean up the EAL */
+ rte_eal_cleanup();
+
+ return 0;
}