#include "main.h"
-#define MAX_QUEUES 256
+#define MAX_QUEUES 512
/* 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 */
/* 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_BADDR((mb)->buf_addr) != (mb))
+
/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
static uint32_t zero_copy;
static int mergeable;
+/* Do vlan strip on host, enabled on default */
+static uint32_t vlan_strip = 1;
+
/* number of descriptors to apply*/
static uint32_t num_rx_descriptor = RTE_TEST_RX_DESC_DEFAULT_ZCP;
static uint32_t num_tx_descriptor = RTE_TEST_TX_DESC_DEFAULT_ZCP;
/* 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 = {
{
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);
+ if (dev_info.max_rx_queues > MAX_QUEUES) {
+ rte_exit(EXIT_FAILURE,
+ "please define MAX_QUEUES no less than %u in %s\n",
+ dev_info.max_rx_queues, __FILE__);
+ }
+
+ rxconf = &dev_info.default_rxconf;
+ txconf = &dev_info.default_txconf;
+ rxconf->rx_drop_en = 1;
+
+ /* Enable vlan offload */
+ txconf->txq_flags &= ~ETH_TXQ_FLAGS_NOVLANOFFL;
+
+ /*
+ * Zero copy defers queue RX/TX start to the time when guest
+ * finishes its startup and packet buffers from that guest are
+ * available.
+ */
+ if (zero_copy) {
+ rxconf->rx_deferred_start = 1;
+ rxconf->rx_drop_en = 0;
+ txconf->tx_deferred_start = 1;
+ }
+
/*configure the number of supported virtio devices based on VMDQ limits */
num_devices = dev_info.max_vmdq_pools;
/* 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;
}
" --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 "
{"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},
}
}
+ /* 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;
+ }
+ }
+
/* Enable/disable stats. */
if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
return -1;
} else
zero_copy = ret;
-
- if (zero_copy) {
-#ifdef RTE_MBUF_REFCNT
- RTE_LOG(ERR, VHOST_CONFIG, "Before running "
- "zero copy vhost APP, please "
- "disable RTE_MBUF_REFCNT\n"
- "in config file and then rebuild DPDK "
- "core lib!\n"
- "Otherwise please disable zero copy "
- "flag in command line!\n");
- return -1;
-#endif
- }
}
/* Specify the descriptor number on RX. */
dev->device_fh);
/* Enable stripping of the vlan tag as we handle routing. */
- rte_eth_dev_set_vlan_strip_on_queue(ports[0], (uint16_t)vdev->vmdq_rx_q, 1);
+ if (vlan_strip)
+ rte_eth_dev_set_vlan_strip_on_queue(ports[0],
+ (uint16_t)vdev->vmdq_rx_q, 1);
/* Set device as ready for RX. */
vdev->ready = DEVICE_RX;
unsigned len, ret, offset = 0;
const uint16_t lcore_id = rte_lcore_id();
struct virtio_net *dev = vdev->dev;
+ struct ether_hdr *nh;
/*check if destination is local VM*/
if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0)) {
return;
}
- if (vm2vm_mode == VM2VM_HARDWARE) {
- if (find_local_dest(dev, m, &offset, &vlan_tag) != 0 ||
- offset > rte_pktmbuf_tailroom(m)) {
+ if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) {
+ if (unlikely(find_local_dest(dev, m, &offset, &vlan_tag) != 0)) {
rte_pktmbuf_free(m);
return;
}
tx_q = &lcore_tx_queue[lcore_id];
len = tx_q->len;
- m->ol_flags = PKT_TX_VLAN_PKT;
+ nh = rte_pktmbuf_mtod(m, struct ether_hdr *);
+ if (unlikely(nh->ether_type == rte_cpu_to_be_16(ETHER_TYPE_VLAN))) {
+ /* Guest has inserted the vlan tag. */
+ struct vlan_hdr *vh = (struct vlan_hdr *) (nh + 1);
+ uint16_t vlan_tag_be = rte_cpu_to_be_16(vlan_tag);
+ if ((vm2vm_mode == VM2VM_HARDWARE) &&
+ (vh->vlan_tci != vlan_tag_be))
+ vh->vlan_tci = vlan_tag_be;
+ } else {
+ m->ol_flags = PKT_TX_VLAN_PKT;
+
+ /*
+ * Find the right seg to adjust the data len when offset is
+ * bigger than tail room size.
+ */
+ if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) {
+ if (likely(offset <= rte_pktmbuf_tailroom(m)))
+ m->data_len += offset;
+ else {
+ struct rte_mbuf *seg = m;
+
+ while ((seg->next != NULL) &&
+ (offset > rte_pktmbuf_tailroom(seg)))
+ seg = seg->next;
- m->data_len += offset;
- m->pkt_len += offset;
+ seg->data_len += offset;
+ }
+ m->pkt_len += offset;
+ }
- m->vlan_tci = vlan_tag;
+ m->vlan_tci = vlan_tag;
+ }
tx_q->m_table[len] = m;
len++;
/* 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)
+ rte_pktmbuf_free(pkts_burst[--tx_count]);
}
}
while (tx_count)
/* Kick the guest if necessary. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
+ eventfd_write((int)vq->callfd, 1);
}
/*
for (index = 0; index < mbuf_count; index++) {
mbuf = __rte_mbuf_raw_alloc(vpool->pool);
- if (likely(RTE_MBUF_INDIRECT(mbuf)))
+ if (likely(MBUF_EXT_MEM(mbuf)))
pktmbuf_detach_zcp(mbuf);
rte_ring_sp_enqueue(vpool->ring, mbuf);
/* Kick guest if required. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
+ eventfd_write((int)vq->callfd, 1);
return 0;
}
for (index = 0; index < mbuf_count; index++) {
mbuf = __rte_mbuf_raw_alloc(vpool->pool);
if (likely(mbuf != NULL)) {
- if (likely(RTE_MBUF_INDIRECT(mbuf)))
+ if (likely(MBUF_EXT_MEM(mbuf)))
pktmbuf_detach_zcp(mbuf);
rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
}
/* Kick the guest if necessary. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
+ eventfd_write((int)vq->callfd, 1);
return count;
}
}
- vdev->regions_hpa = (struct virtio_memory_regions_hpa *) rte_zmalloc("vhost hpa region",
- sizeof(struct virtio_memory_regions_hpa) * vdev->nregions_hpa,
- 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);
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;