[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
[VHOST_USER_POSTCOPY_ADVISE] = "VHOST_USER_POSTCOPY_ADVISE",
[VHOST_USER_POSTCOPY_LISTEN] = "VHOST_USER_POSTCOPY_LISTEN",
+ [VHOST_USER_POSTCOPY_END] = "VHOST_USER_POSTCOPY_END",
};
+static int send_vhost_reply(int sockfd, struct VhostUserMsg *msg);
+static int read_vhost_message(int sockfd, struct VhostUserMsg *msg);
+
static uint64_t
get_blk_size(int fd)
{
int main_fd __rte_unused)
{
struct virtio_net *dev = *pdev;
- dev->virtqueue[msg->payload.state.index]->last_used_idx =
- msg->payload.state.num;
- dev->virtqueue[msg->payload.state.index]->last_avail_idx =
- msg->payload.state.num;
+ struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
+ uint64_t val = msg->payload.state.num;
+
+ if (vq_is_packed(dev)) {
+ /*
+ * Bit[0:14]: avail index
+ * Bit[15]: avail wrap counter
+ */
+ vq->last_avail_idx = val & 0x7fff;
+ vq->avail_wrap_counter = !!(val & (0x1 << 15));
+ /*
+ * Set used index to same value as available one, as
+ * their values should be the same since ring processing
+ * was stopped at get time.
+ */
+ vq->last_used_idx = vq->last_avail_idx;
+ vq->used_wrap_counter = vq->avail_wrap_counter;
+ } else {
+ vq->last_used_idx = msg->payload.state.num;
+ vq->last_avail_idx = msg->payload.state.num;
+ }
return VH_RESULT_OK;
}
static int
vhost_user_set_mem_table(struct virtio_net **pdev, struct VhostUserMsg *msg,
- int main_fd __rte_unused)
+ int main_fd)
{
struct virtio_net *dev = *pdev;
- struct VhostUserMemory memory = msg->payload.memory;
+ struct VhostUserMemory *memory = &msg->payload.memory;
struct rte_vhost_mem_region *reg;
void *mmap_addr;
uint64_t mmap_size;
int populate;
int fd;
- if (memory.nregions > VHOST_MEMORY_MAX_NREGIONS) {
+ if (memory->nregions > VHOST_MEMORY_MAX_NREGIONS) {
RTE_LOG(ERR, VHOST_CONFIG,
- "too many memory regions (%u)\n", memory.nregions);
+ "too many memory regions (%u)\n", memory->nregions);
return VH_RESULT_ERR;
}
- if (dev->mem && !vhost_memory_changed(&memory, dev->mem)) {
+ if (dev->mem && !vhost_memory_changed(memory, dev->mem)) {
RTE_LOG(INFO, VHOST_CONFIG,
"(%d) memory regions not changed\n", dev->vid);
- for (i = 0; i < memory.nregions; i++)
+ for (i = 0; i < memory->nregions; i++)
close(msg->fds[i]);
return VH_RESULT_OK;
}
dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct rte_vhost_memory) +
- sizeof(struct rte_vhost_mem_region) * memory.nregions, 0);
+ sizeof(struct rte_vhost_mem_region) * memory->nregions, 0);
if (dev->mem == NULL) {
RTE_LOG(ERR, VHOST_CONFIG,
"(%d) failed to allocate memory for dev->mem\n",
dev->vid);
return VH_RESULT_ERR;
}
- dev->mem->nregions = memory.nregions;
+ dev->mem->nregions = memory->nregions;
- for (i = 0; i < memory.nregions; i++) {
+ for (i = 0; i < memory->nregions; i++) {
fd = msg->fds[i];
reg = &dev->mem->regions[i];
- reg->guest_phys_addr = memory.regions[i].guest_phys_addr;
- reg->guest_user_addr = memory.regions[i].userspace_addr;
- reg->size = memory.regions[i].memory_size;
+ reg->guest_phys_addr = memory->regions[i].guest_phys_addr;
+ reg->guest_user_addr = memory->regions[i].userspace_addr;
+ reg->size = memory->regions[i].memory_size;
reg->fd = fd;
- mmap_offset = memory.regions[i].mmap_offset;
+ mmap_offset = memory->regions[i].mmap_offset;
/* Check for memory_size + mmap_offset overflow */
if (mmap_offset >= -reg->size) {
mmap_offset);
if (dev->postcopy_listening) {
+ /*
+ * We haven't a better way right now than sharing
+ * DPDK's virtual address with Qemu, so that Qemu can
+ * retrieve the region offset when handling userfaults.
+ */
+ memory->regions[i].userspace_addr =
+ reg->host_user_addr;
+ }
+ }
+ if (dev->postcopy_listening) {
+ /* Send the addresses back to qemu */
+ msg->fd_num = 0;
+ send_vhost_reply(main_fd, msg);
+
+ /* Wait for qemu to acknolwedge it's got the addresses
+ * we've got to wait before we're allowed to generate faults.
+ */
+ VhostUserMsg ack_msg;
+ if (read_vhost_message(main_fd, &ack_msg) <= 0) {
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "Failed to read qemu ack on postcopy set-mem-table\n");
+ goto err_mmap;
+ }
+ if (ack_msg.request.master != VHOST_USER_SET_MEM_TABLE) {
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "Bad qemu ack on postcopy set-mem-table (%d)\n",
+ ack_msg.request.master);
+ goto err_mmap;
+ }
+
+ /* Now userfault register and we can use the memory */
+ for (i = 0; i < memory->nregions; i++) {
#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+ reg = &dev->mem->regions[i];
struct uffdio_register reg_struct;
- reg_struct.range.start = (uint64_t)(uintptr_t)mmap_addr;
- reg_struct.range.len = mmap_size;
+ /*
+ * Let's register all the mmap'ed area to ensure
+ * alignment on page boundary.
+ */
+ reg_struct.range.start =
+ (uint64_t)(uintptr_t)reg->mmap_addr;
+ reg_struct.range.len = reg->mmap_size;
reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
if (ioctl(dev->postcopy_ufd, UFFDIO_REGISTER,
{
struct virtio_net *dev = *pdev;
struct vhost_virtqueue *vq = dev->virtqueue[msg->payload.state.index];
+ uint64_t val;
/* We have to stop the queue (virtio) if it is running. */
vhost_destroy_device_notify(dev);
dev->flags &= ~VIRTIO_DEV_READY;
dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED;
- /* Here we are safe to get the last avail index */
- msg->payload.state.num = vq->last_avail_idx;
+ /* Here we are safe to get the indexes */
+ if (vq_is_packed(dev)) {
+ /*
+ * Bit[0:14]: avail index
+ * Bit[15]: avail wrap counter
+ */
+ val = vq->last_avail_idx & 0x7fff;
+ val |= vq->avail_wrap_counter << 15;
+ msg->payload.state.num = val;
+ } else {
+ msg->payload.state.num = vq->last_avail_idx;
+ }
RTE_LOG(INFO, VHOST_CONFIG,
"vring base idx:%d file:%d\n", msg->payload.state.index,
{
struct virtio_net *dev = *pdev;
uint64_t protocol_features = msg->payload.u64;
- if (protocol_features & ~VHOST_USER_PROTOCOL_FEATURES) {
+ uint64_t slave_protocol_features = 0;
+
+ rte_vhost_driver_get_protocol_features(dev->ifname,
+ &slave_protocol_features);
+ if (protocol_features & ~slave_protocol_features) {
RTE_LOG(ERR, VHOST_CONFIG,
"(%d) received invalid protocol features.\n",
dev->vid);
return VH_RESULT_OK;
}
+static int
+vhost_user_postcopy_end(struct virtio_net **pdev, struct VhostUserMsg *msg,
+ int main_fd __rte_unused)
+{
+ struct virtio_net *dev = *pdev;
+
+ dev->postcopy_listening = 0;
+ if (dev->postcopy_ufd >= 0) {
+ close(dev->postcopy_ufd);
+ dev->postcopy_ufd = -1;
+ }
+
+ msg->payload.u64 = 0;
+ msg->size = sizeof(msg->payload.u64);
+ msg->fd_num = 0;
+
+ return VH_RESULT_REPLY;
+}
+
typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
struct VhostUserMsg *msg,
int main_fd);
[VHOST_USER_IOTLB_MSG] = vhost_user_iotlb_msg,
[VHOST_USER_POSTCOPY_ADVISE] = vhost_user_set_postcopy_advise,
[VHOST_USER_POSTCOPY_LISTEN] = vhost_user_set_postcopy_listen,
+ [VHOST_USER_POSTCOPY_END] = vhost_user_postcopy_end,
};
if (ret <= 0)
return ret;
- if (msg && msg->size) {
+ if (msg->size) {
if (msg->size > sizeof(msg->payload)) {
RTE_LOG(ERR, VHOST_CONFIG,
"invalid msg size: %d\n", msg->size);