/*-
* BSD LICENSE
*
- * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
+ * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
/* 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+1)*MBUF_CACHE_SIZE))
-
#define MBUF_CACHE_SIZE 128
#define MBUF_DATA_SIZE RTE_MBUF_DEFAULT_BUF_SIZE
#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
/* 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
-
/* 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;
/* Disable TSO offload */
static uint32_t enable_tso;
+static int client_mode;
+
/* 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 = {
/* ethernet addresses of ports */
static struct 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. */
/* TX queue for each data core. */
struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE];
+#define MBUF_TABLE_DRAIN_TSC ((rte_get_tsc_hz() + US_PER_S - 1) \
+ / US_PER_S * BURST_TX_DRAIN_US)
#define VLAN_HLEN 4
-/* Per-device statistics struct */
-struct device_statistics {
- uint64_t tx_total;
- rte_atomic64_t rx_total_atomic;
- uint64_t tx;
- rte_atomic64_t rx_atomic;
-} __rte_cache_aligned;
-struct device_statistics dev_statistics[MAX_DEVICES];
-
/*
* Builds up the correct configuration for VMDQ VLAN pool map
* according to the pool & queue limits.
if (enable_tso == 0) {
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4);
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO6);
+ rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_GUEST_TSO4);
+ rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_GUEST_TSO6);
}
rx_rings = (uint16_t)dev_info.max_rx_queues;
/* Configure ethernet device. */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
- if (retval != 0)
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT, "Failed to configure port %u: %s.\n",
+ port, strerror(-retval));
return retval;
+ }
/* Setup the queues. */
for (q = 0; q < rx_rings; q ++) {
rte_eth_dev_socket_id(port),
rxconf,
mbuf_pool);
- if (retval < 0)
+ 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;
+ }
}
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;
}
}
/*
- * 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)
{
/* parse number string */
-
- if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ)
+ if (strnlen(q_arg, PATH_MAX) > PATH_MAX)
return -1;
- else
- snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);
+
+ socket_files = realloc(socket_files, PATH_MAX * (nb_sockets + 1));
+ snprintf(socket_files + nb_sockets * PATH_MAX, PATH_MAX, "%s", q_arg);
+ nb_sockets++;
return 0;
}
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"
" --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"
+ " --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",
prgname);
}
{"mergeable", required_argument, NULL, 0},
{"vlan-strip", required_argument, NULL, 0},
{"stats", required_argument, NULL, 0},
- {"dev-basename", required_argument, NULL, 0},
+ {"socket-file", required_argument, NULL, 0},
{"tx-csum", required_argument, NULL, 0},
{"tso", required_argument, NULL, 0},
+ {"client", no_argument, &client_mode, 1},
{NULL, 0, 0, 0},
};
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");
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for stats [0..N]\n");
us_vhost_usage(prgname);
return -1;
} else {
}
}
- /* 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);
+ /* Set socket file path. */
+ if (!strncmp(long_option[option_index].name,
+ "socket-file", MAX_LONG_OPT_SZ)) {
+ 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;
}
return valid_num_ports;
}
-/*
- * 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)
+static inline struct vhost_dev *__attribute__((always_inline))
+find_vhost_dev(struct ether_addr *mac)
{
- return ((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0;
+ struct vhost_dev *vdev;
+
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ if (vdev->ready == DEVICE_RX &&
+ is_same_ether_addr(mac, &vdev->mac_address))
+ return vdev;
+ }
+
+ return NULL;
}
/*
link_vmdq(struct vhost_dev *vdev, struct rte_mbuf *m)
{
struct ether_hdr *pkt_hdr;
- struct virtio_net_data_ll *dev_ll;
- struct virtio_net *dev = vdev->dev;
int i, ret;
/* Learn MAC address of guest device from packet */
pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- dev_ll = ll_root_used;
-
- while (dev_ll != NULL) {
- if (ether_addr_cmp(&(pkt_hdr->s_addr), &dev_ll->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->s_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];
/* 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,
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) mac %02x:%02x:%02x:%02x:%02x:%02x and vlan %d registered\n",
+ vdev->vid,
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],
/* 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)
}
}
+static inline void __attribute__((always_inline))
+virtio_xmit(struct vhost_dev *dst_vdev, struct vhost_dev *src_vdev,
+ struct rte_mbuf *m)
+{
+ uint16_t ret;
+
+ ret = rte_vhost_enqueue_burst(dst_vdev->vid, VIRTIO_RXQ, &m, 1);
+ if (enable_stats) {
+ rte_atomic64_inc(&dst_vdev->stats.rx_total_atomic);
+ rte_atomic64_add(&dst_vdev->stats.rx_atomic, ret);
+ src_vdev->stats.tx_total++;
+ src_vdev->stats.tx += ret;
+ }
+}
+
/*
* 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))
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 */
+ struct vhost_dev *dst_vdev;
pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- /*get the used devices list*/
- dev_ll = ll_root_used;
+ dst_vdev = find_vhost_dev(&pkt_hdr->d_addr);
+ if (!dst_vdev)
+ return -1;
- while (dev_ll != NULL) {
- if ((dev_ll->vdev->ready == DEVICE_RX) && ether_addr_cmp(&(pkt_hdr->d_addr),
- &dev_ll->vdev->mac_address)) {
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
+ return 0;
+ }
- /* Drop the packet if the TX packet is destined for the TX device. */
- if (dev_ll->vdev->dev->device_fh == dev->device_fh) {
- RTE_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;
-
-
- RTE_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*/
- RTE_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;
- }
- }
+ RTE_LOG(DEBUG, VHOST_DATA,
+ "(%d) TX: MAC address is local\n", dst_vdev->vid);
- return 0;
- }
- dev_ll = dev_ll->next;
+ if (unlikely(dst_vdev->remove)) {
+ RTE_LOG(DEBUG, VHOST_DATA,
+ "(%d) device is marked for removal\n", dst_vdev->vid);
+ return 0;
}
- return -1;
+ virtio_xmit(dst_vdev, vdev, m);
+ return 0;
}
/*
* 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,
+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 vhost_dev *dst_vdev;
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) {
- RTE_LOG(DEBUG, VHOST_DATA,
- "(%"PRIu64") TX: Source and destination"
- " MAC addresses are the same. Dropping "
- "packet.\n",
- dev_ll->vdev->dev->device_fh);
- return -1;
- }
-
- /*
- * HW vlan strip will reduce the packet length
- * by minus length of vlan tag, so need restore
- * the packet length by plus it.
- */
- *offset = VLAN_HLEN;
- *vlan_tag =
- (uint16_t)
- vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh];
-
- RTE_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->d_addr);
+ if (!dst_vdev)
+ return 0;
- break;
- }
- dev_ll = dev_ll->next;
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
+ return -1;
}
+
+ /*
+ * HW vlan strip will reduce the packet length
+ * by minus length of vlan tag, so need restore
+ * the packet length by plus it.
+ */
+ *offset = VLAN_HLEN;
+ *vlan_tag = vlan_tags[vdev->vid];
+
+ RTE_LOG(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;
}
tcp_hdr->cksum = get_psd_sum(l3_hdr, m->ol_flags);
}
+static inline void
+free_pkts(struct rte_mbuf **pkts, uint16_t n)
+{
+ while (n--)
+ rte_pktmbuf_free(pkts[n]);
+}
+
+static inline void __attribute__((always_inline))
+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))
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;
+
+ nh = rte_pktmbuf_mtod(m, struct ether_hdr *);
+ if (unlikely(is_broadcast_ether_addr(&nh->d_addr))) {
+ struct vhost_dev *vdev2;
+
+ TAILQ_FOREACH(vdev2, &vhost_dev_list, global_vdev_entry) {
+ 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 (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;
}
}
- RTE_LOG(DEBUG, VHOST_DATA, "(%" PRIu64 ") TX: "
- "MAC address is external\n", dev->device_fh);
+ RTE_LOG(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))) {
if (m->ol_flags & PKT_TX_TCP_SEG)
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);
+}
+
+
+static inline void __attribute__((always_inline))
+drain_mbuf_table(struct mbuf_table *tx_q)
+{
+ static uint64_t prev_tsc;
+ uint64_t cur_tsc;
+
+ if (tx_q->len == 0)
+ return;
+
+ cur_tsc = rte_rdtsc();
+ if (unlikely(cur_tsc - prev_tsc > MBUF_TABLE_DRAIN_TSC)) {
+ prev_tsc = cur_tsc;
+
+ RTE_LOG(DEBUG, VHOST_DATA,
+ "TX queue drained after timeout with burst size %u\n",
+ tx_q->len);
+ do_drain_mbuf_table(tx_q);
+ }
+}
+
+static inline void __attribute__((always_inline))
+drain_eth_rx(struct vhost_dev *vdev)
+{
+ uint16_t rx_count, enqueue_count;
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+
+ rx_count = rte_eth_rx_burst(ports[0], vdev->vmdq_rx_q,
+ pkts, MAX_PKT_BURST);
+ if (!rx_count)
+ return;
+
+ /*
+ * 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(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);
+ if (rx_count <= rte_vhost_avail_entries(vdev->vid,
+ VIRTIO_RXQ))
+ break;
}
+ }
- len = 0;
+ enqueue_count = rte_vhost_enqueue_burst(vdev->vid, VIRTIO_RXQ,
+ pkts, rx_count);
+ if (enable_stats) {
+ rte_atomic64_add(&vdev->stats.rx_total_atomic, rx_count);
+ rte_atomic64_add(&vdev->stats.rx_atomic, enqueue_count);
}
- tx_q->len = len;
- return;
+ free_pkts(pkts, rx_count);
}
+
+static inline void __attribute__((always_inline))
+drain_virtio_tx(struct vhost_dev *vdev)
+{
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+ uint16_t count;
+ uint16_t i;
+
+ count = rte_vhost_dequeue_burst(vdev->vid, VIRTIO_TXQ, mbuf_pool,
+ pkts, MAX_PKT_BURST);
+
+ /* 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);
+ }
+
+ for (i = 0; i < count; ++i)
+ virtio_tx_route(vdev, pkts[i], vlan_tags[vdev->vid]);
+}
+
/*
- * 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(__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, 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 ++) {
+ for (i = 0; i < rte_lcore_count(); 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) {
- RTE_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;
- }
+ drain_mbuf_table(tx_q);
- 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.
+ * 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;
+ if (lcore_info[lcore_id].dev_removal_flag == REQUEST_DEV_REMOVAL)
+ lcore_info[lcore_id].dev_removal_flag = ACK_DEV_REMOVAL;
/*
- * Process devices
+ * Process vhost devices
*/
- dev_ll = lcore_ll->ll_root_used;
-
- while (dev_ll != NULL) {
- /*get virtio device ID*/
- vdev = dev_ll->vdev;
- dev = vdev->dev;
-
+ 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)) {
- /*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 (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]);
- }
- }
- for (i = 0; i < tx_count; ++i) {
- virtio_tx_route(vdev, pkts_burst[i],
- vlan_tags[(uint16_t)dev->device_fh]);
- }
- }
+ if (likely(vdev->ready == DEVICE_RX))
+ drain_eth_rx(vdev);
- /*move to the next device in the list*/
- dev_ll = dev_ll->next;
+ if (likely(!vdev->remove))
+ drain_virtio_tx(vdev);
}
}
}
/*
- * Add an entry to a used linked list. A free entry must first be found
- * in the free linked list using get_data_ll_free_entry();
- */
-static void
-add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- /* Set next as NULL and use a compiler barrier to avoid reordering. */
- ll_dev->next = NULL;
- rte_compiler_barrier();
-
- /* If ll == NULL then this is the first device. */
- if (ll) {
- /* Increment to the tail of the linked list. */
- while ((ll->next != NULL) )
- ll = ll->next;
-
- ll->next = ll_dev;
- } else {
- *ll_root_addr = ll_dev;
- }
-}
-
-/*
- * Remove an entry from a used linked list. The entry must then be added to
- * the free linked list using put_data_ll_free_entry().
- */
-static void
-rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev,
- struct virtio_net_data_ll *ll_dev_last)
-{
- struct virtio_net_data_ll *ll = *ll_root_addr;
-
- if (unlikely((ll == NULL) || (ll_dev == NULL)))
- return;
-
- if (ll_dev == ll)
- *ll_root_addr = ll_dev->next;
- else
- if (likely(ll_dev_last != NULL))
- ll_dev_last->next = ll_dev->next;
- else
- RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n");
-}
-
-/*
- * Find and return an entry from the free linked list.
- */
-static struct virtio_net_data_ll *
-get_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
- struct virtio_net_data_ll *ll_dev;
-
- if (ll_free == NULL)
- return NULL;
-
- ll_dev = ll_free;
- *ll_root_addr = ll_free->next;
-
- return ll_dev;
-}
-
-/*
- * Place an entry back on to the free linked list.
- */
-static void
-put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr,
- struct virtio_net_data_ll *ll_dev)
-{
- struct virtio_net_data_ll *ll_free = *ll_root_addr;
-
- if (ll_dev == NULL)
- return;
-
- ll_dev->next = ll_free;
- *ll_root_addr = ll_dev;
-}
-
-/*
- * Creates a linked list of a given size.
- */
-static struct virtio_net_data_ll *
-alloc_data_ll(uint32_t size)
-{
- struct virtio_net_data_ll *ll_new;
- uint32_t i;
-
- /* Malloc and then chain the linked list. */
- ll_new = malloc(size * sizeof(struct virtio_net_data_ll));
- if (ll_new == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for ll_new.\n");
- return NULL;
- }
-
- for (i = 0; i < size - 1; i++) {
- ll_new[i].vdev = NULL;
- ll_new[i].next = &ll_new[i+1];
- }
- ll_new[i].next = NULL;
-
- return ll_new;
-}
-
-/*
- * Create the main linked list along with each individual cores linked list. A used and a free list
- * are created to manage entries.
- */
-static int
-init_data_ll (void)
-{
- int lcore;
-
- RTE_LCORE_FOREACH_SLAVE(lcore) {
- lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info));
- if (lcore_info[lcore].lcore_ll == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n");
- return -1;
- }
-
- lcore_info[lcore].lcore_ll->device_num = 0;
- lcore_info[lcore].lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
- lcore_info[lcore].lcore_ll->ll_root_used = NULL;
- if (num_devices % num_switching_cores)
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll((num_devices / num_switching_cores) + 1);
- else
- lcore_info[lcore].lcore_ll->ll_root_free = alloc_data_ll(num_devices / num_switching_cores);
- }
-
- /* Allocate devices up to a maximum of MAX_DEVICES. */
- ll_root_free = alloc_data_ll(MIN((num_devices), MAX_DEVICES));
-
- return 0;
-}
-
-/*
- * Remove a device from the specific data core linked list and from the main linked list. Synchonization
- * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
+ * 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;
- 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;
- }
- }
-
- if (ll_lcore_dev_cur == NULL) {
- RTE_LOG(ERR, VHOST_CONFIG,
- "(%"PRIu64") Failed to find the dev to be destroy.\n",
- dev->device_fh);
- return;
- }
-
- /* Search for entry to be removed from main ll */
- ll_main_dev_cur = ll_root_used;
- ll_main_dev_last = NULL;
- while (ll_main_dev_cur != NULL) {
- if (ll_main_dev_cur->vdev == vdev) {
- break;
- } else {
- ll_main_dev_last = ll_main_dev_cur;
- ll_main_dev_cur = ll_main_dev_cur->next;
- }
- }
+ 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_SLAVE(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) {
+ 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--;
+ lcore_info[vdev->coreid].device_num--;
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) device has been removed from data core\n",
+ vdev->vid);
rte_free(vdev);
-
}
/*
* and the 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;
uint32_t device_num_min = num_devices;
struct vhost_dev *vdev;
vdev = rte_zmalloc("vhost device", sizeof(*vdev), RTE_CACHE_LINE_SIZE);
if (vdev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Couldn't allocate memory for vhost dev\n",
- dev->device_fh);
- return -1;
- }
- vdev->dev = dev;
- dev->priv = vdev;
-
- /* Add device to main ll */
- ll_dev = get_data_ll_free_entry(&ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
- "of %d devices per core has been reached\n",
- dev->device_fh, num_devices);
- rte_free(vdev);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) couldn't allocate memory for vhost dev\n",
+ vid);
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;
+ vdev->vid = vid;
+
+ TAILQ_INSERT_TAIL(&vhost_dev_list, vdev, global_vdev_entry);
+ vdev->vmdq_rx_q = vid * queues_per_pool + vmdq_queue_base;
/*reset ready flag*/
vdev->ready = DEVICE_MAC_LEARNING;
/* 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;
+ if (lcore_info[lcore].device_num < device_num_min) {
+ device_num_min = lcore_info[lcore].device_num;
core_add = lcore;
}
}
- /* Add device to lcore ll */
- ll_dev = get_data_ll_free_entry(&lcore_info[core_add].lcore_ll->ll_root_free);
- if (ll_dev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
- vdev->ready = DEVICE_SAFE_REMOVE;
- destroy_device(dev);
- rte_free(vdev);
- return -1;
- }
- ll_dev->vdev = vdev;
vdev->coreid = core_add;
- add_data_ll_entry(&lcore_info[vdev->coreid].lcore_ll->ll_root_used, ll_dev);
-
- /* Initialize device stats */
- memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics));
+ TAILQ_INSERT_TAIL(&lcore_info[vdev->coreid].vdev_list, vdev,
+ lcore_vdev_entry);
+ lcore_info[vdev->coreid].device_num++;
/* Disable notifications. */
- rte_vhost_enable_guest_notification(dev, VIRTIO_RXQ, 0);
- rte_vhost_enable_guest_notification(dev, VIRTIO_TXQ, 0);
- lcore_info[vdev->coreid].lcore_ll->device_num++;
- dev->flags |= VIRTIO_DEV_RUNNING;
+ rte_vhost_enable_guest_notification(vid, VIRTIO_RXQ, 0);
+ rte_vhost_enable_guest_notification(vid, VIRTIO_TXQ, 0);
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, vdev->coreid);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) device has been added to data core %d\n",
+ vid, vdev->coreid);
return 0;
}
static void
print_stats(void)
{
- 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("%s%s\n", clr, top_left);
+ printf("Device statistics =================================\n");
- printf("\nDevice statistics ====================================");
-
- dev_ll = ll_root_used;
- while (dev_ll != NULL) {
- device_fh = (uint32_t)dev_ll->vdev->dev->device_fh;
- tx_total = dev_statistics[device_fh].tx_total;
- tx = dev_statistics[device_fh].tx;
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ tx_total = vdev->stats.tx_total;
+ tx = vdev->stats.tx;
tx_dropped = tx_total - tx;
- rx_total = rte_atomic64_read(
- &dev_statistics[device_fh].rx_total_atomic);
- rx = rte_atomic64_read(
- &dev_statistics[device_fh].rx_atomic);
+
+ rx_total = rte_atomic64_read(&vdev->stats.rx_total_atomic);
+ rx = rte_atomic64_read(&vdev->stats.rx_atomic);
rx_dropped = rx_total - rx;
- printf("\nStatistics for device %"PRIu32" ------------------------------"
- "\nTX total: %"PRIu64""
- "\nTX dropped: %"PRIu64""
- "\nTX successful: %"PRIu64""
- "\nRX total: %"PRIu64""
- "\nRX dropped: %"PRIu64""
- "\nRX successful: %"PRIu64"",
- device_fh,
- tx_total,
- tx_dropped,
- tx,
- rx_total,
- rx_dropped,
- rx);
-
- dev_ll = dev_ll->next;
+ printf("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");
+ }
+}
+
+static void
+unregister_drivers(int socket_num)
+{
+ int i, ret;
+
+ 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);
}
+/*
+ * 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) * MAX_PKT_BURST;
+ 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. The CUSE
* device is also registered here to handle the IOCTLs.
{
unsigned lcore_id, core_id = 0;
unsigned nb_ports, valid_num_ports;
- int ret;
+ int ret, i;
uint8_t portid;
static pthread_t tid;
char thread_name[RTE_MAX_THREAD_NAME_LEN];
+ uint64_t flags = 0;
signal(SIGINT, sigint_handler);
rte_exit(EXIT_FAILURE, "Invalid argument\n");
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;
if (rte_lcore_count() > RTE_MAX_LCORE)
rte_exit(EXIT_FAILURE,"Not enough cores\n");
- /*set the number of swithcing cores available*/
- num_switching_cores = rte_lcore_count()-1;
-
/* Get the number of physical ports. */
nb_ports = rte_eth_dev_count();
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
/*
* Update the global var NUM_PORTS and global array PORTS
return -1;
}
- /* 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");
+ /*
+ * 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. */
"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);
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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"Cannot set print-stats name\n");
}
if (mergeable == 0)
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF);
- /* 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 (client_mode)
+ flags |= RTE_VHOST_USER_CLIENT;
+
+ /* Register vhost user driver to handle vhost messages. */
+ for (i = 0; i < nb_sockets; i++) {
+ ret = rte_vhost_driver_register
+ (socket_files + i * PATH_MAX, flags);
+ if (ret != 0) {
+ unregister_drivers(i);
+ rte_exit(EXIT_FAILURE,
+ "vhost driver register failure.\n");
+ }
+ }
rte_vhost_driver_callback_register(&virtio_net_device_ops);