#include "main.h"
-#define MAX_QUEUES 128
+#define MAX_QUEUES 256
/* the maximum number of external ports supported */
#define MAX_SUP_PORTS 1
+ RTE_PKTMBUF_HEADROOM)
#define MBUF_CACHE_SIZE_ZCP 0
-/*
- * RX and TX Prefetch, Host, and Write-back threshold values should be
- * carefully set for optimal performance. Consult the network
- * controller's datasheet and supporting DPDK documentation for guidance
- * on how these parameters should be set.
- */
-#define RX_PTHRESH 8 /* Default values of RX prefetch threshold reg. */
-#define RX_HTHRESH 8 /* Default values of RX host threshold reg. */
-#define RX_WTHRESH 4 /* Default values of RX write-back threshold reg. */
-
-/*
- * These default values are optimized for use with the Intel(R) 82599 10 GbE
- * Controller and the DPDK ixgbe PMD. Consider using other values for other
- * network controllers and/or network drivers.
- */
-#define TX_PTHRESH 36 /* Default values of TX prefetch threshold reg. */
-#define TX_HTHRESH 0 /* Default values of TX host threshold reg. */
-#define TX_WTHRESH 0 /* Default values of TX write-back threshold reg. */
-
#define MAX_PKT_BURST 32 /* Max burst size for RX/TX */
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
#define MAC_ADDR_CMP 0xFFFFFFFFFFFFULL
/* Number of descriptors per cacheline. */
-#define DESC_PER_CACHELINE (CACHE_LINE_SIZE / sizeof(struct vring_desc))
+#define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc))
/* 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;
/* Character device basename. Can be set by user. */
static char dev_basename[MAX_BASENAME_SZ] = "vhost-net";
-
-/* Default configuration for rx and tx thresholds etc. */
-static struct rte_eth_rxconf rx_conf_default = {
- .rx_thresh = {
- .pthresh = RX_PTHRESH,
- .hthresh = RX_HTHRESH,
- .wthresh = RX_WTHRESH,
- },
- .rx_drop_en = 1,
-};
-
-/*
- * These default values are optimized for use with the Intel(R) 82599 10 GbE
- * Controller and the DPDK ixgbe/igb PMD. Consider using other values for other
- * network controllers and/or network drivers.
- */
-static struct rte_eth_txconf tx_conf_default = {
- .tx_thresh = {
- .pthresh = TX_PTHRESH,
- .hthresh = TX_HTHRESH,
- .wthresh = TX_WTHRESH,
- },
- .tx_free_thresh = 0, /* Use PMD default values */
- .tx_rs_thresh = 0, /* Use PMD default values */
-};
-
/* empty vmdq configuration structure. Filled in programatically */
static struct rte_eth_conf vmdq_conf_default = {
.rxmode = {
static unsigned lcore_ids[RTE_MAX_LCORE];
static uint8_t ports[RTE_MAX_ETHPORTS];
static unsigned num_ports = 0; /**< The number of ports specified in command line */
+static uint16_t num_pf_queues, num_vmdq_queues;
+static uint16_t vmdq_pool_base, vmdq_queue_base;
+static uint16_t queues_per_pool;
static const uint16_t external_pkt_default_vlan_tag = 2000;
const uint16_t vlan_tags[] = {
get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_devices)
{
struct rte_eth_vmdq_rx_conf conf;
+ struct rte_eth_vmdq_rx_conf *def_conf =
+ &vmdq_conf_default.rx_adv_conf.vmdq_rx_conf;
unsigned i;
memset(&conf, 0, sizeof(conf));
conf.nb_queue_pools = (enum rte_eth_nb_pools)num_devices;
conf.nb_pool_maps = num_devices;
- conf.enable_loop_back =
- vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back;
+ conf.enable_loop_back = def_conf->enable_loop_back;
+ conf.rx_mode = def_conf->rx_mode;
for (i = 0; i < conf.nb_pool_maps; i++) {
conf.pool_map[i].vlan_id = vlan_tags[ i ];
{
struct rte_eth_dev_info dev_info;
struct rte_eth_conf port_conf;
- uint16_t rx_rings, tx_rings;
+ struct rte_eth_rxconf *rxconf;
+ struct rte_eth_txconf *txconf;
+ int16_t rx_rings, tx_rings;
uint16_t rx_ring_size, tx_ring_size;
int retval;
uint16_t q;
/* The max pool number from dev_info will be used to validate the pool number specified in cmd line */
rte_eth_dev_info_get (port, &dev_info);
+ rxconf = &dev_info.default_rxconf;
+ txconf = &dev_info.default_txconf;
+ rxconf->rx_drop_en = 1;
+
+ /*
+ * Zero copy defers queue RX/TX start to the time when guest
+ * finishes its startup and packet buffers from that guest are
+ * available.
+ */
+ if (zero_copy) {
+ rxconf->rx_deferred_start = 1;
+ rxconf->rx_drop_en = 0;
+ txconf->tx_deferred_start = 1;
+ }
+
/*configure the number of supported virtio devices based on VMDQ limits */
num_devices = dev_info.max_vmdq_pools;
- num_queues = dev_info.max_rx_queues;
if (zero_copy) {
rx_ring_size = num_rx_descriptor;
retval = get_eth_conf(&port_conf, num_devices);
if (retval < 0)
return retval;
+ /* NIC queues are divided into pf queues and vmdq queues. */
+ num_pf_queues = dev_info.max_rx_queues - dev_info.vmdq_queue_num;
+ queues_per_pool = dev_info.vmdq_queue_num / dev_info.max_vmdq_pools;
+ num_vmdq_queues = num_devices * queues_per_pool;
+ num_queues = num_pf_queues + num_vmdq_queues;
+ vmdq_queue_base = dev_info.vmdq_queue_base;
+ vmdq_pool_base = dev_info.vmdq_pool_base;
+ printf("pf queue num: %u, configured vmdq pool num: %u, each vmdq pool has %u queues\n",
+ num_pf_queues, num_devices, queues_per_pool);
if (port >= rte_eth_dev_count()) return -1;
- rx_rings = (uint16_t)num_queues,
+ rx_rings = (uint16_t)dev_info.max_rx_queues;
/* Configure ethernet device. */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
if (retval != 0)
/* Setup the queues. */
for (q = 0; q < rx_rings; q ++) {
retval = rte_eth_rx_queue_setup(port, q, rx_ring_size,
- rte_eth_dev_socket_id(port), &rx_conf_default,
+ rte_eth_dev_socket_id(port),
+ rxconf,
vpool_array[q].pool);
if (retval < 0)
return retval;
}
for (q = 0; q < tx_rings; q ++) {
retval = rte_eth_tx_queue_setup(port, q, tx_ring_size,
- rte_eth_dev_socket_id(port), &tx_conf_default);
+ rte_eth_dev_socket_id(port),
+ txconf);
if (retval < 0)
return retval;
}
return retval;
}
+ if (promiscuous)
+ rte_eth_promiscuous_enable(port);
+
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
};
/* Parse command line */
- while ((opt = getopt_long(argc, argv, "p:",long_option, &option_index)) != EOF) {
+ while ((opt = getopt_long(argc, argv, "p:P",
+ long_option, &option_index)) != EOF) {
switch (opt) {
/* Portmask */
case 'p':
}
break;
+ case 'P':
+ promiscuous = 1;
+ vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.rx_mode =
+ ETH_VMDQ_ACCEPT_BROADCAST |
+ ETH_VMDQ_ACCEPT_MULTICAST;
+ rte_vhost_feature_enable(1ULL << VIRTIO_NET_F_CTRL_RX);
+
+ break;
+
case 0:
/* Enable/disable vm2vm comms. */
if (!strncmp(long_option[option_index].name, "vm2vm",
vdev->vlan_tag);
/* Register the MAC address. */
- ret = rte_eth_dev_mac_addr_add(ports[0], &vdev->mac_address, (uint32_t)dev->device_fh);
+ ret = rte_eth_dev_mac_addr_add(ports[0], &vdev->mac_address,
+ (uint32_t)dev->device_fh + vmdq_pool_base);
if (ret)
RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
dev->device_fh);
return -1;
}
+/*
+ * Check if the destination MAC of a packet is one local VM,
+ * and get its vlan tag, and offset if it is.
+ */
+static inline int __attribute__((always_inline))
+find_local_dest(struct virtio_net *dev, struct rte_mbuf *m,
+ uint32_t *offset, uint16_t *vlan_tag)
+{
+ struct virtio_net_data_ll *dev_ll = ll_root_used;
+ struct ether_hdr *pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
+
+ while (dev_ll != NULL) {
+ if ((dev_ll->vdev->ready == DEVICE_RX)
+ && ether_addr_cmp(&(pkt_hdr->d_addr),
+ &dev_ll->vdev->mac_address)) {
+ /*
+ * Drop the packet if the TX packet is
+ * destined for the TX device.
+ */
+ if (dev_ll->vdev->dev->device_fh == dev->device_fh) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: Source and destination"
+ " MAC addresses are the same. Dropping "
+ "packet.\n",
+ dev_ll->vdev->dev->device_fh);
+ return -1;
+ }
+
+ /*
+ * HW vlan strip will reduce the packet length
+ * by minus length of vlan tag, so need restore
+ * the packet length by plus it.
+ */
+ *offset = VLAN_HLEN;
+ *vlan_tag =
+ (uint16_t)
+ vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh];
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: pkt to local VM device id:"
+ "(%"PRIu64") vlan tag: %d.\n",
+ dev->device_fh, dev_ll->vdev->dev->device_fh,
+ vlan_tag);
+
+ break;
+ }
+ dev_ll = dev_ll->next;
+ }
+ return 0;
+}
+
/*
* This function routes the TX packet to the correct interface. This may be a local device
* or the physical port.
struct rte_mbuf **m_table;
unsigned len, ret, offset = 0;
const uint16_t lcore_id = rte_lcore_id();
- struct virtio_net_data_ll *dev_ll = ll_root_used;
- struct ether_hdr *pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
struct virtio_net *dev = vdev->dev;
/*check if destination is local VM*/
}
if (vm2vm_mode == VM2VM_HARDWARE) {
- 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);
- rte_pktmbuf_free(m);
- return;
- }
-
- /*
- * HW vlan strip will reduce the packet length
- * by minus length of vlan tag, so need restore
- * the packet length by plus it.
- */
- offset = VLAN_HLEN;
- vlan_tag =
- (uint16_t)
- vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh];
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") TX: pkt to local VM device id:"
- "(%"PRIu64") vlan tag: %d.\n",
- dev->device_fh, dev_ll->vdev->dev->device_fh,
- vlan_tag);
-
- break;
- }
- dev_ll = dev_ll->next;
+ if (find_local_dest(dev, m, &offset, &vlan_tag) != 0 ||
+ offset > rte_pktmbuf_tailroom(m)) {
+ rte_pktmbuf_free(m);
+ return;
}
}
struct rte_mbuf *mbuf = NULL;
unsigned len, ret, offset = 0;
struct vpool *vpool;
- struct virtio_net_data_ll *dev_ll = ll_root_used;
- struct ether_hdr *pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
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;
* such a ambiguous situation, so pkt will lost.
*/
vlan_tag = external_pkt_default_vlan_tag;
- while (dev_ll != NULL) {
- if (likely(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 (unlikely(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);
- MBUF_HEADROOM_UINT32(mbuf)
- = (uint32_t)desc_idx;
- __rte_mbuf_raw_free(mbuf);
- return;
- }
-
- /*
- * Packet length offset 4 bytes for HW vlan
- * strip when L2 switch back.
- */
- offset = 4;
- vlan_tag =
- (uint16_t)
- vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh];
-
- LOG_DEBUG(VHOST_DATA,
- "(%"PRIu64") TX: pkt to local VM device id:"
- "(%"PRIu64") vlan tag: %d.\n",
- dev->device_fh, dev_ll->vdev->dev->device_fh,
- vlan_tag);
-
- break;
- }
- dev_ll = dev_ll->next;
+ if (find_local_dest(dev, m, &offset, &vlan_tag) != 0) {
+ MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
+ __rte_mbuf_raw_free(mbuf);
+ return;
}
}
/* Buffer address translation. */
buff_addr = gpa_to_vva(dev, desc->addr);
- phys_addr = gpa_to_hpa(vdev, desc->addr, desc->len, &addr_type);
+ /* 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. */
struct vhost_dev *vdev;
uint32_t regionidx;
- vdev = rte_zmalloc("vhost device", sizeof(*vdev), CACHE_LINE_SIZE);
+ 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);
vdev->regions_hpa = (struct virtio_memory_regions_hpa *) rte_zmalloc("vhost hpa region",
sizeof(struct virtio_memory_regions_hpa) * vdev->nregions_hpa,
- CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE);
if (vdev->regions_hpa == NULL) {
RTE_LOG(ERR, VHOST_CONFIG, "Cannot allocate memory for hpa region\n");
rte_free(vdev);
ll_dev->vdev = vdev;
add_data_ll_entry(&ll_root_used, ll_dev);
vdev->vmdq_rx_q
- = dev->device_fh * (num_queues / num_devices);
+ = dev->device_fh * queues_per_pool + vmdq_queue_base;
if (zero_copy) {
uint32_t index = vdev->vmdq_rx_q;
* device is also registered here to handle the IOCTLs.
*/
int
-MAIN(int argc, char *argv[])
+main(int argc, char *argv[])
{
struct rte_mempool *mbuf_pool = NULL;
unsigned lcore_id, core_id = 0;
unsigned nb_ports, valid_num_ports;
int ret;
- uint8_t portid, queue_id = 0;
+ uint8_t portid;
+ uint16_t queue_id;
static pthread_t tid;
/* init EAL */
char pool_name[RTE_MEMPOOL_NAMESIZE];
char ring_name[RTE_MEMPOOL_NAMESIZE];
- /*
- * Zero copy defers queue RX/TX start to the time when guest
- * finishes its startup and packet buffers from that guest are
- * available.
- */
- rx_conf_default.rx_deferred_start = (uint8_t)zero_copy;
- rx_conf_default.rx_drop_en = 0;
- tx_conf_default.tx_deferred_start = (uint8_t)zero_copy;
nb_mbuf = num_rx_descriptor
+ num_switching_cores * MBUF_CACHE_SIZE_ZCP
+ num_switching_cores * MAX_PKT_BURST;
}
LOG_DEBUG(VHOST_CONFIG,
- "in MAIN: mbuf count in mempool at initial "
+ "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 :"
+ "in main: mbuf count in ring at initial is :"
" %d\n",
rte_ring_count(vpool_array[index].ring));
}
git.droids-corp.org / dpdk.git / blobdiff