#include <rte_log.h>
#include <rte_string_fns.h>
#include <rte_malloc.h>
+#include <rte_virtio_net.h>
#include "main.h"
-#include "virtio-net.h"
-#include "vhost-net-cdev.h"
#define MAX_QUEUES 128
/* Character device basename. Can be set by user. */
static char dev_basename[MAX_BASENAME_SZ] = "vhost-net";
-/* Charater device index. Can be set by user. */
-static uint32_t dev_index = 0;
/* This can be set by the user so it is made available here. */
extern uint64_t VHOST_FEATURES;
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> --dev-index [0-N]\n"
+ " --dev-basename <name>\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"
" --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"
- " --dev-index [0-N]: Defaults to zero if not used. Index is appended to basename.\n"
" --zero-copy [0|1]: disable(default)/enable rx/tx "
"zero copy\n"
" --rx-desc-num [0-N]: the number of descriptors on rx, "
{"mergeable", required_argument, NULL, 0},
{"stats", required_argument, NULL, 0},
{"dev-basename", required_argument, NULL, 0},
- {"dev-index", required_argument, NULL, 0},
{"zero-copy", required_argument, NULL, 0},
{"rx-desc-num", required_argument, NULL, 0},
{"tx-desc-num", required_argument, NULL, 0},
}
}
- /* Set character device index. */
- if (!strncmp(long_option[option_index].name, "dev-index", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, INT32_MAX);
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device index [0..N]\n");
- us_vhost_usage(prgname);
- return -1;
- } else
- dev_index = ret;
- }
-
/* Enable/disable rx/tx zero copy. */
if (!strncmp(long_option[option_index].name,
"zero-copy", MAX_LONG_OPT_SZ)) {
/*drop the packet if the device is marked for removal*/
LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", tdev->device_fh);
} else {
- uint32_t mergeable =
- dev_ll->dev->features &
- (1 << VIRTIO_NET_F_MRG_RXBUF);
-
/*send the packet to the local virtio device*/
- if (likely(mergeable == 0))
- ret = virtio_dev_rx(dev_ll->dev, &m, 1);
- else
- ret = virtio_dev_merge_rx(dev_ll->dev,
- &m, 1);
-
+ ret = rte_vhost_enqueue_burst(tdev, VIRTIO_RXQ, &m, 1);
if (enable_stats) {
rte_atomic64_add(
&dev_statistics[tdev->device_fh].rx_total_atomic,
* or the physical port.
*/
static inline void __attribute__((always_inline))
-virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, struct rte_mempool *mbuf_pool, uint16_t vlan_tag)
+virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, uint16_t vlan_tag)
{
struct mbuf_table *tx_q;
- struct vlan_ethhdr *vlan_hdr;
struct rte_mbuf **m_table;
- struct rte_mbuf *mbuf, *prev;
unsigned len, ret, offset = 0;
const uint16_t lcore_id = rte_lcore_id();
struct virtio_net_data_ll *dev_ll = ll_root_used;
struct virtio_net *dev = vdev->dev;
/*check if destination is local VM*/
- if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0))
+ if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(vdev, m) == 0)) {
+ rte_pktmbuf_free(m);
return;
+ }
if (vm2vm_mode == VM2VM_HARDWARE) {
while (dev_ll != NULL) {
"(%"PRIu64") TX: Source and destination"
" MAC addresses are the same. Dropping "
"packet.\n",
- dev_ll->vdev->device_fh);
+ dev_ll->vdev->dev->device_fh);
+ rte_pktmbuf_free(m);
return;
}
offset = 4;
tx_q = &lcore_tx_queue[lcore_id];
len = tx_q->len;
- /* Allocate an mbuf and populate the structure. */
- mbuf = rte_pktmbuf_alloc(mbuf_pool);
- if (unlikely(mbuf == NULL)) {
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
- return;
- }
+ m->ol_flags = PKT_TX_VLAN_PKT;
+ /*FIXME: offset*/
+ m->data_len += offset;
+ m->vlan_tci = vlan_tag;
- mbuf->data_len = m->data_len + VLAN_HLEN + offset;
- mbuf->pkt_len = m->pkt_len + VLAN_HLEN + offset;
- mbuf->nb_segs = m->nb_segs;
-
- /* Copy ethernet header to mbuf. */
- 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 = 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 *)(rte_pktmbuf_mtod(mbuf, uint8_t *) + VLAN_ETH_HLEN),
- (const void *)(rte_pktmbuf_mtod(m, uint8_t *) + ETH_HLEN),
- (m->data_len - ETH_HLEN));
-
- /* Copy the remaining segments for the whole packet. */
- prev = mbuf;
- while (m->next) {
- /* Allocate an mbuf and populate the structure. */
- struct rte_mbuf *next_mbuf = rte_pktmbuf_alloc(mbuf_pool);
- if (unlikely(next_mbuf == NULL)) {
- rte_pktmbuf_free(mbuf);
- RTE_LOG(ERR, VHOST_DATA,
- "Failed to allocate memory for mbuf.\n");
- return;
- }
-
- m = m->next;
- prev->next = next_mbuf;
- prev = next_mbuf;
- next_mbuf->data_len = m->data_len;
-
- /* Copy data to next mbuf. */
- rte_memcpy(rte_pktmbuf_mtod(next_mbuf, void *),
- rte_pktmbuf_mtod(m, const void *), m->data_len);
- }
-
- tx_q->m_table[len] = mbuf;
+ tx_q->m_table[len] = m;
len++;
if (enable_stats) {
dev_statistics[dev->device_fh].tx_total++;
const uint16_t lcore_id = rte_lcore_id();
const uint16_t num_cores = (uint16_t)rte_lcore_count();
uint16_t rx_count = 0;
- uint32_t mergeable = 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;
/*get virtio device ID*/
vdev = dev_ll->vdev;
dev = vdev->dev;
- mergeable =
- dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF);
if (vdev->remove) {
dev_ll = dev_ll->next;
vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
if (rx_count) {
- if (likely(mergeable == 0))
- ret_count =
- virtio_dev_rx(dev,
- pkts_burst, rx_count);
- else
- ret_count =
- virtio_dev_merge_rx(dev,
- pkts_burst, 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,
}
if (!vdev->remove) {
- /*Handle guest TX*/
- if (likely(mergeable == 0))
- virtio_dev_tx(dev, mbuf_pool);
- else
- virtio_dev_merge_tx(dev, mbuf_pool);
+ /* 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]);
+ }
+ }
+ while (tx_count)
+ virtio_tx_route(vdev, pkts_burst[--tx_count], (uint16_t)dev->device_fh);
}
/*move to the next device in the list*/
dev->device_fh);
mbuf_destroy_zcp(vpool);
+ rte_free(vdev->regions_hpa);
}
rte_free(vdev);
}
+/*
+ * Calculate the region count of physical continous regions for one particular
+ * region of whose vhost virtual address is continous. The particular region
+ * start from vva_start, with size of 'size' in argument.
+ */
+static uint32_t
+check_hpa_regions(uint64_t vva_start, uint64_t size)
+{
+ 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,
+ "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,
+ "in check_countinous: "
+ "size((%"PRIu64")) mod page_size(%d) has remainder\n",
+ size, page_size);
+ return 0;
+ }
+ for (i = 0; i < size - page_size; i = i + page_size) {
+ cur_phys_addr
+ = rte_mem_virt2phy((void *)(uintptr_t)(vva_start + i));
+ next_phys_addr = rte_mem_virt2phy(
+ (void *)(uintptr_t)(vva_start + i + page_size));
+ if ((cur_phys_addr + page_size) != next_phys_addr) {
+ ++nregions;
+ 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,
+ "in check_continuous: hpa addr:(%p) is not "
+ "continuous with hpa addr:(%p), "
+ "diff:(%"PRIu64")\n",
+ (void *)(uintptr_t)cur_phys_addr,
+ (void *)(uintptr_t)next_phys_addr,
+ (next_phys_addr-cur_phys_addr));
+ }
+ }
+ return nregions;
+}
+
+/*
+ * Divide each region whose vhost virtual address is continous into a few
+ * sub-regions, make sure the physical address within each sub-region are
+ * continous. And fill offset(to GPA) and size etc. information of each
+ * sub-region into regions_hpa.
+ */
+static uint32_t
+fill_hpa_memory_regions(struct virtio_memory_regions_hpa *mem_region_hpa, struct virtio_memory *virtio_memory)
+{
+ uint32_t regionidx, regionidx_hpa = 0, i, k, page_size = getpagesize();
+ uint64_t cur_phys_addr = 0, next_phys_addr = 0, vva_start;
+
+ if (mem_region_hpa == NULL)
+ return 0;
+
+ for (regionidx = 0; regionidx < virtio_memory->nregions; regionidx++) {
+ vva_start = virtio_memory->regions[regionidx].guest_phys_address +
+ virtio_memory->regions[regionidx].address_offset;
+ mem_region_hpa[regionidx_hpa].guest_phys_address
+ = virtio_memory->regions[regionidx].guest_phys_address;
+ 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,
+ "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,
+ "in fill_hpa_regions: host phys addr start[%d]:(%p)\n",
+ regionidx_hpa,
+ (void *)(uintptr_t)
+ (mem_region_hpa[regionidx_hpa].host_phys_addr_offset));
+ for (i = 0, k = 0;
+ i < virtio_memory->regions[regionidx].memory_size -
+ page_size;
+ i += page_size) {
+ cur_phys_addr = rte_mem_virt2phy(
+ (void *)(uintptr_t)(vva_start + i));
+ next_phys_addr = rte_mem_virt2phy(
+ (void *)(uintptr_t)(vva_start +
+ i + page_size));
+ if ((cur_phys_addr + page_size) != next_phys_addr) {
+ mem_region_hpa[regionidx_hpa].guest_phys_address_end =
+ 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 [%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 [%d]:(%p)\n",
+ regionidx_hpa,
+ (void *)(uintptr_t)
+ (mem_region_hpa[regionidx_hpa].memory_size));
+ mem_region_hpa[regionidx_hpa + 1].guest_phys_address
+ = mem_region_hpa[regionidx_hpa].guest_phys_address_end;
+ ++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"
+ " phys addr start[%d]:(%p)\n",
+ regionidx_hpa,
+ (void *)(uintptr_t)
+ (mem_region_hpa[regionidx_hpa].guest_phys_address));
+ LOG_DEBUG(VHOST_CONFIG,
+ "in fill_hpa_regions: host phys addr "
+ "start[%d]:(%p)\n",
+ regionidx_hpa,
+ (void *)(uintptr_t)
+ (mem_region_hpa[regionidx_hpa].host_phys_addr_offset));
+ k = 0;
+ } else {
+ k += page_size;
+ }
+ }
+ mem_region_hpa[regionidx_hpa].guest_phys_address_end
+ = 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 "
+ "[%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 "
+ "[%d]:(%p)\n", regionidx_hpa,
+ (void *)(uintptr_t)
+ (mem_region_hpa[regionidx_hpa].memory_size));
+ ++regionidx_hpa;
+ }
+ return regionidx_hpa;
+}
+
/*
* A new device is added to a data core. First the device is added to the main linked list
* and the allocated to a specific data core.
int lcore, core_add = 0;
uint32_t device_num_min = num_devices;
struct vhost_dev *vdev;
+ uint32_t regionidx;
vdev = rte_zmalloc("vhost device", sizeof(*vdev), CACHE_LINE_SIZE);
if (vdev == NULL) {
vdev->dev = dev;
dev->priv = vdev;
+ if (zero_copy) {
+ vdev->nregions_hpa = dev->mem->nregions;
+ for (regionidx = 0; regionidx < dev->mem->nregions; regionidx++) {
+ vdev->nregions_hpa
+ += check_hpa_regions(
+ dev->mem->regions[regionidx].guest_phys_address
+ + dev->mem->regions[regionidx].address_offset,
+ dev->mem->regions[regionidx].memory_size);
+
+ }
+
+ 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);
+ if (vdev->regions_hpa == NULL) {
+ RTE_LOG(ERR, VHOST_CONFIG, "Cannot allocate memory for hpa region\n");
+ rte_free(vdev);
+ return -1;
+ }
+
+
+ if (fill_hpa_memory_regions(
+ vdev->regions_hpa, dev->mem
+ ) != vdev->nregions_hpa) {
+
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "hpa memory regions number mismatch: "
+ "[%d]\n", vdev->nregions_hpa);
+ rte_free(vdev->regions_hpa);
+ rte_free(vdev);
+ return -1;
+ }
+ }
+
+
/* 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);
+ if (vdev->regions_hpa)
+ rte_free(vdev->regions_hpa);
rte_free(vdev);
return -1;
}
dev->device_fh, vdev->vmdq_rx_q);
mbuf_destroy_zcp(vpool);
+ rte_free(vdev->regions_hpa);
rte_free(vdev);
return -1;
}
}
mbuf_destroy_zcp(vpool);
+ rte_free(vdev->regions_hpa);
rte_free(vdev);
return -1;
}
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);
return -1;
}
}
/* Register CUSE device to handle IOCTLs. */
- ret = register_cuse_device((char*)&dev_basename, dev_index, get_virtio_net_callbacks());
+ ret = rte_vhost_driver_register((char *)&dev_basename);
if (ret != 0)
rte_exit(EXIT_FAILURE,"CUSE device setup failure.\n");
- init_virtio_net(&virtio_net_device_ops);
+ rte_vhost_driver_callback_register(&virtio_net_device_ops);
/* Start CUSE session. */
- start_cuse_session_loop();
+ rte_vhost_driver_session_start();
return 0;
}