/*-
* 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_string_fns.h>
#include <rte_malloc.h>
#include <rte_virtio_net.h>
+#include <rte_ip.h>
+#include <rte_tcp.h>
#include "main.h"
-#define MAX_QUEUES 512
+#ifndef MAX_QUEUES
+#define MAX_QUEUES 128
+#endif
/* 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) + \
+#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))
+ ((num_switching_cores+1)*MBUF_CACHE_SIZE))
-#define MBUF_CACHE_SIZE 128
-#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)
+#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 1518
-#define MBUF_SIZE_ZCP (VIRTIO_DESCRIPTOR_LEN_ZCP + sizeof(struct rte_mbuf) \
- + RTE_PKTMBUF_HEADROOM)
+#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 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 BURST_RX_WAIT_US 15 /* Defines how long we wait between retries on RX */
#define BURST_RX_RETRIES 4 /* Number of retries on RX. */
#define JUMBO_FRAME_MAX_SIZE 0x2600
/* 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;
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;
static uint32_t enable_stats = 0;
/* Enable retries on RX. */
static uint32_t enable_retry = 1;
+
+/* Disable TX checksum offload */
+static uint32_t enable_tx_csum;
+
+/* Disable TSO offload */
+static uint32_t enable_tso;
+
/* 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. */
__be16 h_vlan_encapsulated_proto;
};
-/* IPv4 Header */
-struct ipv4_hdr {
- uint8_t version_ihl; /**< version and header length */
- uint8_t type_of_service; /**< type of service */
- uint16_t total_length; /**< length of packet */
- uint16_t packet_id; /**< packet ID */
- uint16_t fragment_offset; /**< fragmentation offset */
- uint8_t time_to_live; /**< time to live */
- uint8_t next_proto_id; /**< protocol ID */
- uint16_t hdr_checksum; /**< header checksum */
- uint32_t src_addr; /**< source address */
- uint32_t dst_addr; /**< destination address */
-} __attribute__((__packed__));
-
/* Header lengths. */
#define VLAN_HLEN 4
#define VLAN_ETH_HLEN 18
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);
+ }
+
rx_rings = (uint16_t)dev_info.max_rx_queues;
/* Configure ethernet device. */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
" --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-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",
+ "used only when zero copy is enabled.\n"
+ " --tx-csum [0|1] disable/enable TX checksum offload.\n"
+ " --tso [0|1] disable/enable TCP segment offload.\n",
prgname);
}
{"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},
{NULL, 0, 0, 0},
};
}
}
+ /* 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;
+ }
+
+ /* 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;
+ }
+
/* 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);
}
}
+ /* 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. */
* Macro to print out packet contents. Wrapped in debug define so that the
* data path is not effected when debug is disabled.
*/
-#ifdef DEBUG
+#if RTE_LOG_LEVEL >= RTE_LOG_DEBUG
#define PRINT_PACKET(device, addr, size, header) do { \
char *pkt_addr = (char*)(addr); \
unsigned int index; \
} \
snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \
\
- LOG_DEBUG(VHOST_DATA, "%s", packet); \
+ RTE_LOG(DEBUG, VHOST_DATA, "%s", packet); \
} while(0)
#else
#define PRINT_PACKET(device, addr, size, header) do{} while(0)
}
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") GPA %p| HPA %p\n",
+ RTE_LOG(DEBUG, VHOST_DATA, "(%" PRIu64 ") GPA %p| HPA %p\n",
vdev->dev->device_fh, (void *)(uintptr_t)guest_pa,
(void *)(uintptr_t)vhost_pa);
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 ((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0;
}
/*
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;
/* 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);
+ 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;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is local\n", tdev->device_fh);
+ 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*/
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", tdev->device_fh);
+ 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);
rte_atomic64_add(
&dev_statistics[tdev->device_fh].rx_atomic,
ret);
- dev_statistics[tdev->device_fh].tx_total++;
- dev_statistics[tdev->device_fh].tx += ret;
+ dev_statistics[dev->device_fh].tx_total++;
+ dev_statistics[dev->device_fh].tx += ret;
}
}
* destined for the TX device.
*/
if (dev_ll->vdev->dev->device_fh == dev->device_fh) {
- LOG_DEBUG(VHOST_DATA,
+ RTE_LOG(DEBUG, VHOST_DATA,
"(%"PRIu64") TX: Source and destination"
" MAC addresses are the same. Dropping "
"packet.\n",
(uint16_t)
vlan_tags[(uint16_t)dev_ll->vdev->dev->device_fh];
- LOG_DEBUG(VHOST_DATA,
+ 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,
- vlan_tag);
+ (int)*vlan_tag);
break;
}
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);
+}
+
+static void virtio_tx_offload(struct rte_mbuf *m)
+{
+ void *l3_hdr;
+ struct ipv4_hdr *ipv4_hdr = NULL;
+ struct tcp_hdr *tcp_hdr = NULL;
+ struct ether_hdr *eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
+
+ l3_hdr = (char *)eth_hdr + m->l2_len;
+
+ if (m->ol_flags & PKT_TX_IPV4) {
+ ipv4_hdr = l3_hdr;
+ ipv4_hdr->hdr_checksum = 0;
+ m->ol_flags |= PKT_TX_IP_CKSUM;
+ }
+
+ tcp_hdr = (struct tcp_hdr *)((char *)l3_hdr + m->l3_len);
+ tcp_hdr->cksum = get_psd_sum(l3_hdr, m->ol_flags);
+}
+
/*
* This function routes the TX packet to the correct interface. This may be a local device
* or the physical port.
}
}
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);
+ RTE_LOG(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];
(vh->vlan_tci != vlan_tag_be))
vh->vlan_tci = vlan_tag_be;
} else {
- m->ol_flags = PKT_TX_VLAN_PKT;
+ m->ol_flags |= PKT_TX_VLAN_PKT;
/*
* Find the right seg to adjust the data len when offset is
m->vlan_tci = vlan_tag;
}
+ if (m->ol_flags & PKT_TX_TCP_SEG)
+ virtio_tx_offload(m);
+
tx_q->m_table[len] = m;
len++;
if (enable_stats) {
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(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,
rte_pktmbuf_free(pkts_burst[--tx_count]);
}
}
- while (tx_count)
- virtio_tx_route(vdev, pkts_burst[--tx_count], (uint16_t)dev->device_fh);
+ for (i = 0; i < tx_count; ++i) {
+ virtio_tx_route(vdev, pkts_burst[i],
+ vlan_tags[(uint16_t)dev->device_fh]);
+ }
}
/*move to the next device in the list*/
avail_idx = *((volatile uint16_t *)&vq->avail->idx);
free_entries = (avail_idx - *res_base_idx);
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") in get_available_ring_index_zcp: "
+ RTE_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,
count = free_entries;
if (unlikely(count == 0)) {
- LOG_DEBUG(VHOST_DATA,
+ RTE_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,
/* Kick the guest if necessary. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
+ eventfd_write(vq->callfd, (eventfd_t)1);
}
/*
uint64_t buff_addr, phys_addr;
struct vhost_virtqueue *vq;
struct vring_desc *desc;
- struct rte_mbuf *mbuf = NULL;
+ void *obj = NULL;
+ struct rte_mbuf *mbuf;
struct vpool *vpool;
hpa_type addr_type;
struct vhost_dev *vdev = (struct vhost_dev *)dev->priv;
}
} while (unlikely(phys_addr == 0));
- rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
+ rte_ring_sc_dequeue(vpool->ring, &obj);
+ mbuf = obj;
if (unlikely(mbuf == NULL)) {
- LOG_DEBUG(VHOST_DATA,
+ RTE_LOG(DEBUG, VHOST_DATA,
"(%"PRIu64") in attach_rxmbuf_zcp: "
"ring_sc_dequeue fail.\n",
dev->device_fh);
}
if (unlikely(vpool->buf_size > desc->len)) {
- LOG_DEBUG(VHOST_DATA,
+ RTE_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, (void *)mbuf);
+ rte_ring_sp_enqueue(vpool->ring, obj);
return;
}
mbuf->data_len = desc->len;
MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
- LOG_DEBUG(VHOST_DATA,
+ RTE_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);
static inline void pktmbuf_detach_zcp(struct rte_mbuf *m)
{
const struct rte_mempool *mp = m->pool;
- void *buf = RTE_MBUF_TO_BADDR(m);
+ 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);
uint32_t index = 0;
uint32_t mbuf_count = rte_mempool_count(vpool->pool);
- LOG_DEBUG(VHOST_DATA,
+ RTE_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,
+ RTE_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(RTE_MBUF_INDIRECT(mbuf)))
+ if (likely(MBUF_EXT_MEM(mbuf)))
pktmbuf_detach_zcp(mbuf);
rte_ring_sp_enqueue(vpool->ring, mbuf);
used_idx = (used_idx + 1) & (vq->size - 1);
}
- LOG_DEBUG(VHOST_DATA,
+ RTE_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,
+ RTE_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,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_DATA,
"(%"PRIu64") in txmbuf_clean_zcp: after updated "
"vq->last_used_idx:%d\n",
dev->device_fh, vq->last_used_idx);
/* Kick guest if required. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
- eventfd_write((int)vq->kickfd, 1);
+ eventfd_write(vq->callfd, (eventfd_t)1);
return 0;
}
struct rte_mbuf *mbuf = NULL;
uint32_t index, mbuf_count = rte_mempool_count(vpool->pool);
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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,
+ RTE_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(RTE_MBUF_INDIRECT(mbuf)))
+ if (likely(MBUF_EXT_MEM(mbuf)))
pktmbuf_detach_zcp(mbuf);
rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
}
}
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in mbuf_destroy_zcp: mbuf count in ring after "
"mbuf_destroy_zcp is : %d\n",
rte_ring_count(vpool->ring));
uint32_t head_idx, packet_success = 0;
uint16_t res_cur_idx;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
+ RTE_LOG(DEBUG, VHOST_DATA, "(%" PRIu64 ") virtio_dev_rx()\n",
+ dev->device_fh);
if (count == 0)
return 0;
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",
+ RTE_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. */
desc = &vq->desc[head[packet_success]];
buff = pkts[packet_success];
- LOG_DEBUG(VHOST_DATA,
+ RTE_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,
rte_compiler_barrier();
- LOG_DEBUG(VHOST_DATA,
+ RTE_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,
+ RTE_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((int)vq->kickfd, 1);
+ eventfd_write(vq->callfd, (eventfd_t)1);
return count;
}
{
struct mbuf_table *tx_q;
struct rte_mbuf **m_table;
- struct rte_mbuf *mbuf = NULL;
+ 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];
/* Allocate an mbuf and populate the structure. */
vpool = &vpool_array[MAX_QUEUES + vmdq_rx_q];
- rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
+ 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,
mbuf->buf_physaddr = m->buf_physaddr;
mbuf->buf_addr = m->buf_addr;
}
- mbuf->ol_flags = PKT_TX_VLAN_PKT;
+ 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);
tx_q->m_table[len] = mbuf;
len++;
- LOG_DEBUG(VHOST_DATA,
+ RTE_LOG(DEBUG, VHOST_DATA,
"(%"PRIu64") in tx_route_zcp: pkt: nb_seg: %d, next:%s\n",
dev->device_fh,
mbuf->nb_segs,
if (vq->last_used_idx_res == avail_idx)
return;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
+ RTE_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)]);
free_entries
= (free_entries > MAX_PKT_BURST) ? MAX_PKT_BURST : free_entries;
- LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n",
+ RTE_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. */
if (likely(!vdev->remove)) {
tx_q = &tx_queue_zcp[(uint16_t)vdev->vmdq_rx_q];
if (tx_q->len) {
- LOG_DEBUG(VHOST_DATA,
+ RTE_LOG(DEBUG, VHOST_DATA,
"TX queue drained after timeout"
" with burst size %u\n",
tx_q->len);
}
ll_new[i].next = NULL;
- return (ll_new);
+ return ll_new;
}
/*
/* Stop the RX queue. */
if (rte_eth_dev_rx_queue_stop(ports[0], vdev->vmdq_rx_q) != 0) {
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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,
+ RTE_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);
/* Stop the TX queue. */
if (rte_eth_dev_tx_queue_stop(ports[0], vdev->vmdq_rx_q) != 0) {
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"(%"PRIu64") In destroy_device: Failed to "
"stop tx queue:%d\n",
dev->device_fh, vdev->vmdq_rx_q);
vpool = &vpool_array[vdev->vmdq_rx_q + MAX_QUEUES];
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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),
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,
+ RTE_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;
}
if (size % page_size) {
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in check_countinous: "
"size((%"PRIu64")) mod page_size(%d) has remainder\n",
size, page_size);
(void *)(uintptr_t)(vva_start + i + page_size));
if ((cur_phys_addr + page_size) != next_phys_addr) {
++nregions;
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in check_continuous: hpa addr:(%p) is not "
"continuous with hpa addr:(%p), "
"diff:(%"PRIu64")\n",
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,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in fill_hpa_regions: host phys addr start[%d]:(%p)\n",
regionidx_hpa,
(void *)(uintptr_t)
k + page_size;
mem_region_hpa[regionidx_hpa].memory_size
= k + page_size;
- LOG_DEBUG(VHOST_CONFIG, "in fill_hpa_regions: guest "
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in fill_hpa_regions: guest phys addr "
"size [%d]:(%p)\n",
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"
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in fill_hpa_regions: host phys addr "
"start[%d]:(%p)\n",
regionidx_hpa,
= 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 "
+ RTE_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 "
+ RTE_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));
}
- 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);
count_in_ring = rte_ring_count(vpool_array[index].ring);
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"(%"PRIu64") in new_device: mbuf count in ring "
"before attach is : %d\n",
dev->device_fh, count_in_ring);
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",
+ RTE_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",
+ RTE_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));
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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"(%"PRIu64") In new_device: Failed to start "
"tx queue:%d\n",
dev->device_fh, vdev->vmdq_rx_q);
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,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"(%"PRIu64") In new_device: Failed to "
"stop tx queue:%d\n",
dev->device_fh, vdev->vmdq_rx_q);
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);
- if (vdev->regions_hpa)
- rte_free(vdev->regions_hpa);
+ rte_free(vdev->regions_hpa);
rte_free(vdev);
return -1;
}
setup_mempool_tbl(int socket, uint32_t index, char *pool_name,
char *ring_name, uint32_t nb_mbuf)
{
- uint16_t roomsize = VIRTIO_DESCRIPTOR_LEN_ZCP + RTE_PKTMBUF_HEADROOM;
- vpool_array[index].pool
- = rte_mempool_create(pool_name, nb_mbuf, MBUF_SIZE_ZCP,
- MBUF_CACHE_SIZE_ZCP, sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, (void *)(uintptr_t)roomsize,
- rte_pktmbuf_init, NULL, socket, 0);
+ 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,
+ RTE_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,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in setup_mempool_tbl: mbuf count in "
"ring is: %d\n",
rte_ring_count(vpool_array[index].ring));
}
/* Need consider head room. */
- vpool_array[index].buf_size = roomsize - RTE_PKTMBUF_HEADROOM;
+ vpool_array[index].buf_size = VIRTIO_DESCRIPTOR_LEN_ZCP;
} else {
rte_exit(EXIT_FAILURE, "mempool_create(%s) failed", pool_name);
}
}
+/* When we receive a INT signal, unregister vhost driver */
+static void
+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");
+ exit(0);
+}
/*
* Main function, does initialisation and calls the per-lcore functions. The CUSE
uint8_t portid;
uint16_t queue_id;
static pthread_t tid;
+ char thread_name[RTE_MAX_THREAD_NAME_LEN];
+
+ signal(SIGINT, sigint_handler);
/* init EAL */
ret = rte_eal_init(argc, argv);
if (zero_copy == 0) {
/* 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, MBUF_DATA_SIZE, rte_socket_id());
if (mbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\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;
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"Enable loop back for L2 switch in vmdq.\n");
}
} else {
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,
+ 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++) {
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-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) {
(void *)mbuf);
}
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in main: mbuf count in mempool at initial "
"is: %d\n", count_in_mempool);
- LOG_DEBUG(VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"in main: mbuf count in ring at initial is :"
" %d\n",
rte_ring_count(vpool_array[index].ring));
if (mergeable == 0)
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF);
- /* Register CUSE device to handle IOCTLs. */
+ /* 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,"CUSE device setup failure.\n");
+ rte_exit(EXIT_FAILURE, "vhost driver register failure.\n");
rte_vhost_driver_callback_register(&virtio_net_device_ops);
return 0;
}
-
git.droids-corp.org / dpdk.git / blobdiff