#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
-#include <net/ethernet.h>
-#include <netinet/in.h>
-#include <netinet/if_ether.h>
-#include <linux/if_packet.h>
#include <rte_common.h>
#include <rte_log.h>
-#include "virtio-net.h"
#include "virtio-net-user.h"
#include "vhost-net-user.h"
#include "vhost-net.h"
get_blk_size(int fd)
{
struct stat stat;
+ int ret;
- fstat(fd, &stat);
- return (uint64_t)stat.st_blksize;
+ ret = fstat(fd, &stat);
+ return ret == -1 ? (uint64_t)-1 : (uint64_t)stat.st_blksize;
}
static void
free(dev->mem);
dev->mem = NULL;
}
+ if (dev->log_addr) {
+ munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
+ dev->log_addr = 0;
+ }
}
int
-user_set_mem_table(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+user_set_mem_table(int vid, struct VhostUserMsg *pmsg)
{
struct VhostUserMemory memory = pmsg->payload.memory;
struct virtio_memory_regions *pregion;
uint64_t alignment;
/* unmap old memory regions one by one*/
- dev = get_device(ctx);
+ dev = get_device(vid);
if (dev == NULL)
return -1;
/* Remove from the data plane. */
- if (dev->flags & VIRTIO_DEV_RUNNING)
- notify_ops->destroy_device(dev);
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ notify_ops->destroy_device(vid);
+ }
if (dev->mem) {
free_mem_region(dev);
sizeof(struct orig_region_map) * memory.nregions);
if (dev->mem == NULL) {
RTE_LOG(ERR, VHOST_CONFIG,
- "(%"PRIu64") Failed to allocate memory for dev->mem\n",
- dev->device_fh);
+ "(%d) failed to allocate memory for dev->mem\n",
+ dev->vid);
return -1;
}
dev->mem->nregions = memory.nregions;
* aligned.
*/
alignment = get_blk_size(pmsg->fds[idx]);
+ if (alignment == (uint64_t)-1) {
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "couldn't get hugepage size through fstat\n");
+ goto err_mmap;
+ }
mapped_size = RTE_ALIGN_CEIL(mapped_size, alignment);
mapped_address = (uint64_t)(uintptr_t)mmap(NULL,
vq_is_ready(struct vhost_virtqueue *vq)
{
return vq && vq->desc &&
- vq->kickfd != -1 &&
- vq->callfd != -1;
+ vq->kickfd != VIRTIO_UNINITIALIZED_EVENTFD &&
+ vq->callfd != VIRTIO_UNINITIALIZED_EVENTFD;
}
static int
}
void
-user_set_vring_call(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+user_set_vring_call(int vid, struct VhostUserMsg *pmsg)
{
struct vhost_vring_file file;
file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
- file.fd = -1;
+ file.fd = VIRTIO_INVALID_EVENTFD;
else
file.fd = pmsg->fds[0];
RTE_LOG(INFO, VHOST_CONFIG,
"vring call idx:%d file:%d\n", file.index, file.fd);
- vhost_set_vring_call(ctx, &file);
+ vhost_set_vring_call(vid, &file);
}
* device is ready for packet processing.
*/
void
-user_set_vring_kick(struct vhost_device_ctx ctx, struct VhostUserMsg *pmsg)
+user_set_vring_kick(int vid, struct VhostUserMsg *pmsg)
{
struct vhost_vring_file file;
- struct virtio_net *dev = get_device(ctx);
+ struct virtio_net *dev = get_device(vid);
+
+ if (!dev)
+ return;
file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
- file.fd = -1;
+ file.fd = VIRTIO_INVALID_EVENTFD;
else
file.fd = pmsg->fds[0];
RTE_LOG(INFO, VHOST_CONFIG,
"vring kick idx:%d file:%d\n", file.index, file.fd);
- vhost_set_vring_kick(ctx, &file);
+ vhost_set_vring_kick(vid, &file);
- if (virtio_is_ready(dev) &&
- !(dev->flags & VIRTIO_DEV_RUNNING))
- notify_ops->new_device(dev);
+ if (virtio_is_ready(dev) && !(dev->flags & VIRTIO_DEV_RUNNING)) {
+ if (notify_ops->new_device(vid) == 0)
+ dev->flags |= VIRTIO_DEV_RUNNING;
+ }
}
/*
* when virtio is stopped, qemu will send us the GET_VRING_BASE message.
*/
int
-user_get_vring_base(struct vhost_device_ctx ctx,
- struct vhost_vring_state *state)
+user_get_vring_base(int vid, struct vhost_vring_state *state)
{
- struct virtio_net *dev = get_device(ctx);
+ struct virtio_net *dev = get_device(vid);
if (dev == NULL)
return -1;
/* We have to stop the queue (virtio) if it is running. */
if (dev->flags & VIRTIO_DEV_RUNNING)
- notify_ops->destroy_device(dev);
+ notify_ops->destroy_device(vid);
/* Here we are safe to get the last used index */
- vhost_get_vring_base(ctx, state->index, state);
+ vhost_get_vring_base(vid, state->index, state);
RTE_LOG(INFO, VHOST_CONFIG,
"vring base idx:%d file:%d\n", state->index, state->num);
* sent and only sent in vhost_vring_stop.
* TODO: cleanup the vring, it isn't usable since here.
*/
- if (dev->virtqueue[state->index]->kickfd >= 0) {
+ if (dev->virtqueue[state->index]->kickfd >= 0)
close(dev->virtqueue[state->index]->kickfd);
- dev->virtqueue[state->index]->kickfd = -1;
- }
+
+ dev->virtqueue[state->index]->kickfd = VIRTIO_UNINITIALIZED_EVENTFD;
return 0;
}
* enable the virtio queue pair.
*/
int
-user_set_vring_enable(struct vhost_device_ctx ctx,
- struct vhost_vring_state *state)
+user_set_vring_enable(int vid, struct vhost_vring_state *state)
{
- struct virtio_net *dev = get_device(ctx);
+ struct virtio_net *dev;
int enable = (int)state->num;
+ dev = get_device(vid);
+ if (dev == NULL)
+ return -1;
+
RTE_LOG(INFO, VHOST_CONFIG,
"set queue enable: %d to qp idx: %d\n",
enable, state->index);
- if (notify_ops->vring_state_changed) {
- notify_ops->vring_state_changed(dev, state->index, enable);
- }
+ if (notify_ops->vring_state_changed)
+ notify_ops->vring_state_changed(vid, state->index, enable);
dev->virtqueue[state->index]->enabled = enable;
}
void
-user_set_protocol_features(struct vhost_device_ctx ctx,
- uint64_t protocol_features)
+user_set_protocol_features(int vid, uint64_t protocol_features)
{
struct virtio_net *dev;
- dev = get_device(ctx);
+ dev = get_device(vid);
if (dev == NULL || protocol_features & ~VHOST_USER_PROTOCOL_FEATURES)
return;
}
int
-user_set_log_base(struct vhost_device_ctx ctx,
- struct VhostUserMsg *msg)
+user_set_log_base(int vid, struct VhostUserMsg *msg)
{
struct virtio_net *dev;
int fd = msg->fds[0];
uint64_t size, off;
void *addr;
- dev = get_device(ctx);
+ dev = get_device(vid);
if (!dev)
return -1;
* fail when offset is not page size aligned.
*/
addr = mmap(0, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ close(fd);
if (addr == MAP_FAILED) {
RTE_LOG(ERR, VHOST_CONFIG, "mmap log base failed!\n");
return -1;
}
- /* TODO: unmap on stop */
- dev->log_base = (uint64_t)(uintptr_t)addr + off;
+ /*
+ * Free previously mapped log memory on occasionally
+ * multiple VHOST_USER_SET_LOG_BASE.
+ */
+ if (dev->log_addr) {
+ munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
+ }
+ dev->log_addr = (uint64_t)(uintptr_t)addr;
+ dev->log_base = dev->log_addr + off;
dev->log_size = size;
return 0;
}
-#define RARP_BUF_SIZE 64
-
-static void
-make_rarp_packet(uint8_t *buf, uint8_t *mac)
-{
- struct ether_header *eth_hdr;
- struct ether_arp *rarp;
-
- /* Ethernet header. */
- eth_hdr = (struct ether_header *)buf;
- memset(ð_hdr->ether_dhost, 0xff, ETH_ALEN);
- memcpy(ð_hdr->ether_shost, mac, ETH_ALEN);
- eth_hdr->ether_type = htons(ETH_P_RARP);
-
- /* RARP header. */
- rarp = (struct ether_arp *)(eth_hdr + 1);
- rarp->ea_hdr.ar_hrd = htons(ARPHRD_ETHER);
- rarp->ea_hdr.ar_pro = htons(ETHERTYPE_IP);
- rarp->ea_hdr.ar_hln = ETH_ALEN;
- rarp->ea_hdr.ar_pln = 4;
- rarp->ea_hdr.ar_op = htons(ARPOP_RREQUEST);
-
- memcpy(&rarp->arp_sha, mac, ETH_ALEN);
- memset(&rarp->arp_spa, 0x00, 4);
- memcpy(&rarp->arp_tha, mac, 6);
- memset(&rarp->arp_tpa, 0x00, 4);
-}
-
-
-static void
-send_rarp(const char *ifname, uint8_t *rarp)
-{
- int fd;
- struct ifreq ifr;
- struct sockaddr_ll addr;
-
- fd = socket(AF_PACKET, SOCK_RAW, 0);
- if (fd < 0) {
- perror("socket failed");
- return;
- }
-
- memset(&ifr, 0, sizeof(struct ifreq));
- strncpy(ifr.ifr_name, ifname, IFNAMSIZ);
- if (ioctl(fd, SIOCGIFINDEX, &ifr) < 0) {
- perror("failed to get interface index");
- close(fd);
- return;
- }
-
- addr.sll_ifindex = ifr.ifr_ifindex;
- addr.sll_halen = ETH_ALEN;
-
- if (sendto(fd, rarp, RARP_BUF_SIZE, 0,
- (const struct sockaddr*)&addr, sizeof(addr)) < 0) {
- perror("send rarp packet failed");
- }
-}
-
-
/*
- * Broadcast a RARP message to all interfaces, to update
- * switch's mac table
+ * An rarp packet is constructed and broadcasted to notify switches about
+ * the new location of the migrated VM, so that packets from outside will
+ * not be lost after migration.
+ *
+ * However, we don't actually "send" a rarp packet here, instead, we set
+ * a flag 'broadcast_rarp' to let rte_vhost_dequeue_burst() inject it.
*/
int
-user_send_rarp(struct VhostUserMsg *msg)
+user_send_rarp(int vid, struct VhostUserMsg *msg)
{
+ struct virtio_net *dev;
uint8_t *mac = (uint8_t *)&msg->payload.u64;
- uint8_t rarp[RARP_BUF_SIZE];
- struct ifconf ifc = {0, };
- struct ifreq *ifr;
- int nr = 16;
- int fd;
- uint32_t i;
+
+ dev = get_device(vid);
+ if (!dev)
+ return -1;
RTE_LOG(DEBUG, VHOST_CONFIG,
":: mac: %02x:%02x:%02x:%02x:%02x:%02x\n",
mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
-
- make_rarp_packet(rarp, mac);
+ memcpy(dev->mac.addr_bytes, mac, 6);
/*
- * Get all interfaces
+ * Set the flag to inject a RARP broadcast packet at
+ * rte_vhost_dequeue_burst().
+ *
+ * rte_smp_wmb() is for making sure the mac is copied
+ * before the flag is set.
*/
- fd = socket(AF_INET, SOCK_DGRAM, 0);
- if (fd < 0) {
- perror("failed to create AF_INET socket");
- return -1;
- }
-
-again:
- ifc.ifc_len = sizeof(*ifr) * nr;
- ifc.ifc_buf = realloc(ifc.ifc_buf, ifc.ifc_len);
-
- if (ioctl(fd, SIOCGIFCONF, &ifc) < 0) {
- perror("failed at SIOCGIFCONF");
- close(fd);
- return -1;
- }
-
- if (ifc.ifc_len == (int)sizeof(struct ifreq) * nr) {
- /*
- * current ifc_buf is not big enough to hold
- * all interfaces; double it and try again.
- */
- nr *= 2;
- goto again;
- }
-
- ifr = (struct ifreq *)ifc.ifc_buf;
- for (i = 0; i < ifc.ifc_len / sizeof(struct ifreq); i++)
- send_rarp(ifr[i].ifr_name, rarp);
-
- close(fd);
+ rte_smp_wmb();
+ rte_atomic16_set(&dev->broadcast_rarp, 1);
return 0;
}