/*-
* BSD LICENSE
*
- * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <rte_ethdev.h>
#include <rte_log.h>
#include <rte_string_fns.h>
+#include <rte_pause.h>
#include "main.h"
#include "virtio-net.h"
/*
* Calculate the number of buffers needed per port
*/
-#define NUM_MBUFS_PER_PORT ((MAX_QUEUES*RTE_TEST_RX_DESC_DEFAULT) + \
+#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 64
-#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)
/*
* RX and TX Prefetch, Host, and Write-back threshold values should be
#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 MAX_MRG_PKT_BURST 16 /* Max burst for merge buffers. Set to 1 due to performance issue. */
-#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
+#define MAX_PKT_BURST 32 /* Max burst size for RX/TX */
+#define MAX_MRG_PKT_BURST 16 /* Max burst for merge buffers. Set to 1 due to performance issue. */
+#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
/* State of virtio device. */
#define DEVICE_NOT_READY 0
/* Max number of devices. Limited by vmdq. */
#define MAX_DEVICES 64
-/* Size of buffers used for rte_snprintfs. */
+/* Size of buffers used for snprintfs. */
#define MAX_PRINT_BUFF 6072
/* Enable stats. */
static uint32_t enable_stats = 0;
-/* Default configuration for rx and tx thresholds etc. */
-static const struct rte_eth_rxconf rx_conf_default = {
- .rx_thresh = {
- .pthresh = RX_PTHRESH,
- .hthresh = RX_HTHRESH,
- .wthresh = RX_WTHRESH,
- },
- .rx_drop_en = 1,
-};
-
-/*
- * These default values are optimized for use with the Intel(R) 82599 10 GbE
- * Controller and the DPDK ixgbe/igb PMD. Consider using other values for other
- * network controllers and/or network drivers.
- */
-static const struct rte_eth_txconf tx_conf_default = {
- .tx_thresh = {
- .pthresh = TX_PTHRESH,
- .hthresh = TX_HTHRESH,
- .wthresh = TX_WTHRESH,
- },
- .tx_free_thresh = 0, /* Use PMD default values */
- .tx_rs_thresh = 0, /* Use PMD default values */
-};
-
/* empty vmdq configuration structure. Filled in programatically */
static const struct rte_eth_conf vmdq_conf_default = {
.rxmode = {
*/
.hw_vlan_strip = 1, /**< VLAN strip enabled. */
.jumbo_frame = 0, /**< Jumbo Frame Support disabled */
- .hw_strip_crc = 0, /**< CRC stripped by hardware */
+ .hw_strip_crc = 1, /**< CRC stripped by hardware */
},
.txmode = {
port_init(uint8_t port, struct rte_mempool *mbuf_pool)
{
struct rte_eth_dev_info dev_info;
+ struct rte_eth_rxconf *rxconf;
struct rte_eth_conf port_conf;
uint16_t rx_rings, tx_rings = (uint16_t)rte_lcore_count();
- const uint16_t rx_ring_size = RTE_TEST_RX_DESC_DEFAULT, tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
+ uint16_t rx_ring_size = RTE_TEST_RX_DESC_DEFAULT;
+ uint16_t tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
int retval;
uint16_t q;
if (retval != 0)
return retval;
+ retval = rte_eth_dev_adjust_nb_rx_tx_desc(port, &rx_ring_size,
+ &tx_ring_size);
+ if (retval != 0)
+ return retval;
+ if (rx_ring_size > RTE_TEST_RX_DESC_DEFAULT ||
+ tx_ring_size > RTE_TEST_TX_DESC_DEFAULT) {
+ RTE_LOG(ERR, VHOST_PORT, "Mbuf pool has an insufficient size for "
+ "port %u.\n", port);
+ return -1;
+ }
+
+ rte_eth_dev_info_get(port, &dev_info);
+ rxconf = &dev_info.default_rxconf;
+ rxconf->rx_drop_en = 1;
/* 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,
mbuf_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),
+ NULL);
if (retval < 0)
return retval;
}
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)) \
- rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \
- else \
- rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \
- for (index = 0; index < (size); index++) { \
- rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \
- "%02hhx ", pkt_addr[index]); \
- } \
- rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \
- \
- LOG_DEBUG(VHOST_DATA, "%s", packet); \
-} while(0)
-#else
-#define PRINT_PACKET(device, addr, size, header) do{} while(0)
-#endif
-
/*
* Function to convert guest physical addresses to vhost virtual addresses. This
* is used to convert virtio buffer addresses.
*/
-static inline uint64_t __attribute__((always_inline))
+static __rte_always_inline uint64_t
gpa_to_vva(struct virtio_net *dev, uint64_t guest_pa)
{
struct virtio_memory_regions *region;
break;
}
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") GPA %p| VVA %p\n",
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") GPA %p| VVA %p\n",
dev->device_fh, (void*)(uintptr_t)guest_pa, (void*)(uintptr_t)vhost_va);
return vhost_va;
/*
* This function adds buffers to the virtio devices RX virtqueue. Buffers can
* be received from the physical port or from another virtio device. A packet
- * count is returned to indicate the number of packets that were succesfully
+ * count is returned to indicate the number of packets that were successfully
* added to the RX queue.
*/
-static inline uint32_t __attribute__((always_inline))
+static __rte_always_inline uint32_t
virtio_dev_rx(struct virtio_net *dev, struct rte_mbuf **pkts, uint32_t count)
{
struct vhost_virtqueue *vq;
uint16_t res_base_idx, res_end_idx;
uint16_t free_entries;
uint8_t success = 0;
+ void *userdata;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") virtio_dev_rx()\n", dev->device_fh);
vq = dev->virtqueue_rx;
count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count;
/* As many data cores may want access to available buffers, they need to be reserved. */
res_end_idx);
} while (unlikely(success == 0));
res_cur_idx = res_base_idx;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| End Index %d\n", dev->device_fh, res_cur_idx, res_end_idx);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") Current Index %d| End Index %d\n",
+ dev->device_fh, res_cur_idx, res_end_idx);
/* Prefetch available ring to retrieve indexes. */
rte_prefetch0(&vq->avail->ring[res_cur_idx & (vq->size - 1)]);
vq->used->ring[res_cur_idx & (vq->size - 1)].len = packet_len;
/* Copy mbuf data to buffer */
- rte_memcpy((void *)(uintptr_t)buff_addr, (const void*)buff->pkt.data, rte_pktmbuf_data_len(buff));
+ userdata = rte_pktmbuf_mtod(buff, void *);
+ rte_memcpy((void *)(uintptr_t)buff_addr, userdata, rte_pktmbuf_data_len(buff));
res_cur_idx++;
packet_success++;
/* mergeable is disabled then a header is required per buffer. */
- rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen);
+ rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void *)&virtio_hdr, vq->vhost_hlen);
if (res_cur_idx < res_end_idx) {
/* Prefetch descriptor index. */
rte_prefetch0(&vq->desc[head[packet_success]]);
/*
* Compares a packet destination MAC address to a device MAC address.
*/
-static inline int __attribute__((always_inline))
+static __rte_always_inline int
ether_addr_cmp(struct ether_addr *ea, struct ether_addr *eb)
{
- return (((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0);
+ return ((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0;
}
/*
/* Register the MAC address. */
ret = rte_eth_dev_mac_addr_add(ports[0], &dev->mac_address, (uint32_t)dev->device_fh);
- if (ret) {
+ 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 packet destination MAC address is for a local device. If so then put
* the packet on that devices RX queue. If not then return.
*/
-static inline unsigned __attribute__((always_inline))
+static __rte_always_inline unsigned
virtio_tx_local(struct virtio_net *dev, struct rte_mbuf *m)
{
struct virtio_net_data_ll *dev_ll;
struct ether_hdr *pkt_hdr;
uint64_t ret = 0;
- pkt_hdr = (struct ether_hdr *)m->pkt.data;
+ pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
/*get the used devices list*/
dev_ll = ll_root_used;
/* Drop the packet if the TX packet is destined for the TX device. */
if (dev_ll->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->dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") TX: "
+ "Source and destination MAC addresses are the same. "
+ "Dropping packet.\n",
+ dev_ll->dev->device_fh);
return 0;
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is local\n", dev_ll->dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") TX: "
+ "MAC address is local\n", dev_ll->dev->device_fh);
if (dev_ll->dev->remove) {
/*drop the packet if the device is marked for removal*/
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", dev_ll->dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") "
+ "Device is marked for removal\n",
+ dev_ll->dev->device_fh);
} else {
/*send the packet to the local virtio device*/
ret = virtio_dev_rx(dev_ll->dev, &m, 1);
* 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 virtio_net* dev, struct rte_mbuf *m, struct rte_mempool *mbuf_pool, uint16_t vlan_tag)
{
struct mbuf_table *tx_q;
return;
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA, "(%" PRIu64 ") TX: "
+ "MAC address is external\n", dev->device_fh);
/*Add packet to the port tx queue*/
tx_q = &lcore_tx_queue[lcore_id];
if(!mbuf)
return;
- mbuf->pkt.data_len = m->pkt.data_len + VLAN_HLEN;
- mbuf->pkt.pkt_len = mbuf->pkt.data_len;
+ mbuf->data_len = m->data_len + VLAN_HLEN;
+ mbuf->pkt_len = mbuf->data_len;
/* Copy ethernet header to mbuf. */
- rte_memcpy((void*)mbuf->pkt.data, (const void*)m->pkt.data, ETH_HLEN);
+ rte_memcpy(rte_pktmbuf_mtod(mbuf, void*),
+ rte_pktmbuf_mtod(m, const void*), ETH_HLEN);
/* Setup vlan header. Bytes need to be re-ordered for network with htons()*/
- vlan_hdr = (struct vlan_ethhdr *) mbuf->pkt.data;
+ vlan_hdr = rte_pktmbuf_mtod(mbuf, struct vlan_ethhdr *);
vlan_hdr->h_vlan_encapsulated_proto = vlan_hdr->h_vlan_proto;
vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
vlan_hdr->h_vlan_TCI = htons(vlan_tag);
/* Copy the remaining packet contents to the mbuf. */
- rte_memcpy((void*) ((uint8_t*)mbuf->pkt.data + VLAN_ETH_HLEN),
- (const void*) ((uint8_t*)m->pkt.data + ETH_HLEN), (m->pkt.data_len - ETH_HLEN));
+ rte_memcpy(rte_pktmbuf_mtod_offset(mbuf, void *, VLAN_ETH_HLEN),
+ rte_pktmbuf_mtod_offset(m, const void *, ETH_HLEN),
+ (m->data_len - ETH_HLEN));
tx_q->m_table[len] = mbuf;
len++;
if (enable_stats) {
return;
}
-static inline void __attribute__((always_inline))
+static __rte_always_inline void
virtio_dev_tx(struct virtio_net* dev, struct rte_mempool *mbuf_pool)
{
struct rte_mbuf m;
if (vq->last_used_idx == avail_idx)
return;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
+ RTE_LOG_DP(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 & (vq->size - 1)]);
free_entries = avail_idx - vq->last_used_idx;
free_entries = unlikely(free_entries < MAX_PKT_BURST) ? free_entries : MAX_PKT_BURST;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n", dev->device_fh, free_entries);
+ RTE_LOG_DP(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 + i) & (vq->size - 1)];
rte_prefetch0((void*)(uintptr_t)buff_addr);
/* Setup dummy mbuf. This is copied to a real mbuf if transmitted out the physical port. */
- m.pkt.data_len = desc->len;
- m.pkt.data = (void*)(uintptr_t)buff_addr;
- m.pkt.nb_segs = 1;
+ m.data_len = desc->len;
+ m.data_off = 0;
+ m.nb_segs = 1;
virtio_tx_route(dev, &m, mbuf_pool, 0);
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);
+ RTE_LOG_DP(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,
}
ll_new[i].next = NULL;
- return (ll_new);
+ return ll_new;
}
/*
int init_virtio_net(struct virtio_net_device_ops const * const ops);
/*
- * Main function, does initialisation and calls the per-lcore functions. The CUSE
- * device is also registered here to handle the IOCTLs.
+ * Main function, does initialisation and calls the per-lcore functions.
*/
int
-MAIN(int argc, char *argv[])
+main(int argc, char *argv[])
{
struct rte_mempool *mbuf_pool;
unsigned lcore_id, core_id = 0;
int ret;
uint8_t portid;
static pthread_t tid;
+ char thread_name[RTE_MAX_THREAD_NAME_LEN];
/* init EAL */
ret = rte_eal_init(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid argument\n");
- if (rte_eal_pci_probe() != 0)
- rte_exit(EXIT_FAILURE, "Error with NIC driver initialization\n");
-
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++)
if (rte_lcore_is_enabled(lcore_id))
lcore_ids[core_id ++] = lcore_id;
/* 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
- * and get value of var VALID_NUM_PORTS according to system ports number
- */
+ * Update the global var NUM_PORTS and global array PORTS
+ * and get value of var VALID_NUM_PORTS according to system ports number
+ */
valid_num_ports = check_ports_num(nb_ports);
if ((valid_num_ports == 0) || (valid_num_ports > MAX_SUP_PORTS)) {
}
/* Create the mbuf pool. */
- mbuf_pool = rte_mempool_create("MBUF_POOL", NUM_MBUFS_PER_PORT * valid_num_ports,
- MBUF_SIZE, MBUF_CACHE_SIZE,
- sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, NULL,
- rte_pktmbuf_init, NULL,
- rte_socket_id(), 0);
+ mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL",
+ NUM_MBUFS_PER_PORT * valid_num_ports, MBUF_CACHE_SIZE, 0,
+ RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
if (mbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
- /* Set log level. */
- rte_set_log_level(LOG_LEVEL);
-
/* initialize all ports */
for (portid = 0; portid < nb_ports; portid++) {
/* skip ports that are not enabled */
memset(&dev_statistics, 0, sizeof(dev_statistics));
/* Enable stats if the user option is set. */
- if (enable_stats)
- pthread_create(&tid, NULL, (void*)print_stats, NULL );
+ if (enable_stats) {
+ ret = pthread_create(&tid, NULL, (void *)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-xen-stats");
+ ret = rte_thread_setname(tid, thread_name);
+ if (ret != 0)
+ RTE_LOG(DEBUG, VHOST_CONFIG,
+ "Cannot set print-stats name\n");
+ }
/* Launch all data cores. */
RTE_LCORE_FOREACH_SLAVE(lcore_id) {