dev->inflight_info->fd = -1;
}
- free(dev->inflight_info);
+ rte_free(dev->inflight_info);
dev->inflight_info = NULL;
}
if (vq_is_packed(dev)) {
if (vq->shadow_used_packed)
rte_free(vq->shadow_used_packed);
- vq->shadow_used_packed = rte_malloc(NULL,
+ vq->shadow_used_packed = rte_malloc_socket(NULL,
vq->size *
sizeof(struct vring_used_elem_packed),
- RTE_CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE, vq->numa_node);
if (!vq->shadow_used_packed) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for shadow used ring.\n");
if (vq->shadow_used_split)
rte_free(vq->shadow_used_split);
- vq->shadow_used_split = rte_malloc(NULL,
+ vq->shadow_used_split = rte_malloc_socket(NULL,
vq->size * sizeof(struct vring_used_elem),
- RTE_CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE, vq->numa_node);
if (!vq->shadow_used_split) {
VHOST_LOG_CONFIG(ERR,
if (vq->batch_copy_elems)
rte_free(vq->batch_copy_elems);
- vq->batch_copy_elems = rte_malloc(NULL,
+ vq->batch_copy_elems = rte_malloc_socket(NULL,
vq->size * sizeof(struct batch_copy_elem),
- RTE_CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE, vq->numa_node);
if (!vq->batch_copy_elems) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for batching copy.\n");
static struct virtio_net*
numa_realloc(struct virtio_net *dev, int index)
{
- int oldnode, newnode;
+ int node, dev_node;
struct virtio_net *old_dev;
- struct vhost_virtqueue *old_vq, *vq;
- struct vring_used_elem *new_shadow_used_split;
- struct vring_used_elem_packed *new_shadow_used_packed;
- struct batch_copy_elem *new_batch_copy_elems;
+ struct vhost_virtqueue *vq;
+ struct batch_copy_elem *bce;
+ struct guest_page *gp;
+ struct rte_vhost_memory *mem;
+ size_t mem_size;
int ret;
old_dev = dev;
- vq = old_vq = dev->virtqueue[index];
+ vq = dev->virtqueue[index];
/*
* If VQ is ready, it is too late to reallocate, it certainly already
if (vq->ready)
return dev;
- ret = get_mempolicy(&newnode, NULL, 0, old_vq->desc,
- MPOL_F_NODE | MPOL_F_ADDR);
-
- /* check if we need to reallocate vq */
- ret |= get_mempolicy(&oldnode, NULL, 0, old_vq,
- MPOL_F_NODE | MPOL_F_ADDR);
+ ret = get_mempolicy(&node, NULL, 0, vq->desc, MPOL_F_NODE | MPOL_F_ADDR);
if (ret) {
- VHOST_LOG_CONFIG(ERR,
- "Unable to get vq numa information.\n");
+ VHOST_LOG_CONFIG(ERR, "Unable to get virtqueue %d numa information.\n", index);
return dev;
}
- if (oldnode != newnode) {
- VHOST_LOG_CONFIG(INFO,
- "reallocate vq from %d to %d node\n", oldnode, newnode);
- vq = rte_malloc_socket(NULL, sizeof(*vq), 0, newnode);
- if (!vq)
- return dev;
- memcpy(vq, old_vq, sizeof(*vq));
+ if (node == vq->numa_node)
+ goto out_dev_realloc;
- if (vq_is_packed(dev)) {
- new_shadow_used_packed = rte_malloc_socket(NULL,
- vq->size *
- sizeof(struct vring_used_elem_packed),
- RTE_CACHE_LINE_SIZE,
- newnode);
- if (new_shadow_used_packed) {
- rte_free(vq->shadow_used_packed);
- vq->shadow_used_packed = new_shadow_used_packed;
- }
- } else {
- new_shadow_used_split = rte_malloc_socket(NULL,
- vq->size *
- sizeof(struct vring_used_elem),
- RTE_CACHE_LINE_SIZE,
- newnode);
- if (new_shadow_used_split) {
- rte_free(vq->shadow_used_split);
- vq->shadow_used_split = new_shadow_used_split;
- }
- }
+ vq = rte_realloc_socket(vq, sizeof(*vq), 0, node);
+ if (!vq) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc virtqueue %d on node %d\n",
+ index, node);
+ return dev;
+ }
- new_batch_copy_elems = rte_malloc_socket(NULL,
- vq->size * sizeof(struct batch_copy_elem),
- RTE_CACHE_LINE_SIZE,
- newnode);
- if (new_batch_copy_elems) {
- rte_free(vq->batch_copy_elems);
- vq->batch_copy_elems = new_batch_copy_elems;
- }
+ if (vq != dev->virtqueue[index]) {
+ VHOST_LOG_CONFIG(INFO, "reallocated virtqueue on node %d\n", node);
+ dev->virtqueue[index] = vq;
+ vhost_user_iotlb_init(dev, index);
+ }
- if (vq->log_cache) {
- struct log_cache_entry *log_cache;
+ if (vq_is_packed(dev)) {
+ struct vring_used_elem_packed *sup;
- log_cache = rte_realloc_socket(vq->log_cache,
- sizeof(struct log_cache_entry) * VHOST_LOG_CACHE_NR,
- 0, newnode);
- if (log_cache)
- vq->log_cache = log_cache;
+ sup = rte_realloc_socket(vq->shadow_used_packed, vq->size * sizeof(*sup),
+ RTE_CACHE_LINE_SIZE, node);
+ if (!sup) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc shadow packed on node %d\n", node);
+ return dev;
}
+ vq->shadow_used_packed = sup;
+ } else {
+ struct vring_used_elem *sus;
- rte_free(old_vq);
+ sus = rte_realloc_socket(vq->shadow_used_split, vq->size * sizeof(*sus),
+ RTE_CACHE_LINE_SIZE, node);
+ if (!sus) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc shadow split on node %d\n", node);
+ return dev;
+ }
+ vq->shadow_used_split = sus;
}
- if (dev->flags & VIRTIO_DEV_RUNNING)
- goto out;
-
- /* check if we need to reallocate dev */
- ret = get_mempolicy(&oldnode, NULL, 0, old_dev,
- MPOL_F_NODE | MPOL_F_ADDR);
- if (ret) {
- VHOST_LOG_CONFIG(ERR,
- "Unable to get dev numa information.\n");
- goto out;
+ bce = rte_realloc_socket(vq->batch_copy_elems, vq->size * sizeof(*bce),
+ RTE_CACHE_LINE_SIZE, node);
+ if (!bce) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc batch copy elem on node %d\n", node);
+ return dev;
}
- if (oldnode != newnode) {
- struct rte_vhost_memory *old_mem;
- struct guest_page *old_gp;
- ssize_t mem_size, gp_size;
+ vq->batch_copy_elems = bce;
- VHOST_LOG_CONFIG(INFO,
- "reallocate dev from %d to %d node\n",
- oldnode, newnode);
- dev = rte_malloc_socket(NULL, sizeof(*dev), 0, newnode);
- if (!dev) {
- dev = old_dev;
- goto out;
+ if (vq->log_cache) {
+ struct log_cache_entry *lc;
+
+ lc = rte_realloc_socket(vq->log_cache, sizeof(*lc) * VHOST_LOG_CACHE_NR, 0, node);
+ if (!lc) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc log cache on node %d\n", node);
+ return dev;
}
+ vq->log_cache = lc;
+ }
- memcpy(dev, old_dev, sizeof(*dev));
- rte_free(old_dev);
+ if (vq->resubmit_inflight) {
+ struct rte_vhost_resubmit_info *ri;
- mem_size = sizeof(struct rte_vhost_memory) +
- sizeof(struct rte_vhost_mem_region) * dev->mem->nregions;
- old_mem = dev->mem;
- dev->mem = rte_malloc_socket(NULL, mem_size, 0, newnode);
- if (!dev->mem) {
- dev->mem = old_mem;
- goto out;
+ ri = rte_realloc_socket(vq->resubmit_inflight, sizeof(*ri), 0, node);
+ if (!ri) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc resubmit inflight on node %d\n",
+ node);
+ return dev;
}
+ vq->resubmit_inflight = ri;
- memcpy(dev->mem, old_mem, mem_size);
- rte_free(old_mem);
+ if (ri->resubmit_list) {
+ struct rte_vhost_resubmit_desc *rd;
- gp_size = dev->max_guest_pages * sizeof(*dev->guest_pages);
- old_gp = dev->guest_pages;
- dev->guest_pages = rte_malloc_socket(NULL, gp_size, RTE_CACHE_LINE_SIZE, newnode);
- if (!dev->guest_pages) {
- dev->guest_pages = old_gp;
- goto out;
+ rd = rte_realloc_socket(ri->resubmit_list, sizeof(*rd) * ri->resubmit_num,
+ 0, node);
+ if (!rd) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc resubmit list on node %d\n",
+ node);
+ return dev;
+ }
+ ri->resubmit_list = rd;
}
+ }
+
+ vq->numa_node = node;
+
+out_dev_realloc:
- memcpy(dev->guest_pages, old_gp, gp_size);
- rte_free(old_gp);
+ if (dev->flags & VIRTIO_DEV_RUNNING)
+ return dev;
+
+ ret = get_mempolicy(&dev_node, NULL, 0, dev, MPOL_F_NODE | MPOL_F_ADDR);
+ if (ret) {
+ VHOST_LOG_CONFIG(ERR, "Unable to get Virtio dev %d numa information.\n", dev->vid);
+ return dev;
}
-out:
- dev->virtqueue[index] = vq;
+ if (dev_node == node)
+ return dev;
+
+ dev = rte_realloc_socket(old_dev, sizeof(*dev), 0, node);
+ if (!dev) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc dev on node %d\n", node);
+ return old_dev;
+ }
+
+ VHOST_LOG_CONFIG(INFO, "reallocated device on node %d\n", node);
vhost_devices[dev->vid] = dev;
- if (old_vq != vq)
- vhost_user_iotlb_init(dev, index);
+ mem_size = sizeof(struct rte_vhost_memory) +
+ sizeof(struct rte_vhost_mem_region) * dev->mem->nregions;
+ mem = rte_realloc_socket(dev->mem, mem_size, 0, node);
+ if (!mem) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc mem table on node %d\n", node);
+ return dev;
+ }
+ dev->mem = mem;
+
+ gp = rte_realloc_socket(dev->guest_pages, dev->max_guest_pages * sizeof(*gp),
+ RTE_CACHE_LINE_SIZE, node);
+ if (!gp) {
+ VHOST_LOG_CONFIG(ERR, "Failed to realloc guest pages on node %d\n", node);
+ return dev;
+ }
+ dev->guest_pages = gp;
return dev;
}
struct virtio_net *dev = *pdev;
struct VhostUserMemory *memory = &msg->payload.memory;
struct rte_vhost_mem_region *reg;
-
+ int numa_node = SOCKET_ID_ANY;
uint64_t mmap_offset;
uint32_t i;
+ bool async_notify = false;
if (validate_msg_fds(msg, memory->nregions) != 0)
return RTE_VHOST_MSG_RESULT_ERR;
vdpa_dev->ops->dev_close(dev->vid);
dev->flags &= ~VIRTIO_DEV_VDPA_CONFIGURED;
}
+
+ /* notify the vhost application to stop DMA transfers */
+ if (dev->async_copy && dev->notify_ops->vring_state_changed) {
+ for (i = 0; i < dev->nr_vring; i++) {
+ dev->notify_ops->vring_state_changed(dev->vid,
+ i, 0);
+ }
+ async_notify = true;
+ }
+
free_mem_region(dev);
rte_free(dev->mem);
dev->mem = NULL;
for (i = 0; i < dev->nr_vring; i++)
vhost_user_iotlb_flush_all(dev->virtqueue[i]);
+ /*
+ * If VQ 0 has already been allocated, try to allocate on the same
+ * NUMA node. It can be reallocated later in numa_realloc().
+ */
+ if (dev->nr_vring > 0)
+ numa_node = dev->virtqueue[0]->numa_node;
+
dev->nr_guest_pages = 0;
if (dev->guest_pages == NULL) {
dev->max_guest_pages = 8;
- dev->guest_pages = rte_zmalloc(NULL,
+ dev->guest_pages = rte_zmalloc_socket(NULL,
dev->max_guest_pages *
sizeof(struct guest_page),
- RTE_CACHE_LINE_SIZE);
+ RTE_CACHE_LINE_SIZE,
+ numa_node);
if (dev->guest_pages == NULL) {
VHOST_LOG_CONFIG(ERR,
"(%d) failed to allocate memory "
}
}
- dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct rte_vhost_memory) +
- sizeof(struct rte_vhost_mem_region) * memory->nregions, 0);
+ dev->mem = rte_zmalloc_socket("vhost-mem-table", sizeof(struct rte_vhost_memory) +
+ sizeof(struct rte_vhost_mem_region) * memory->nregions, 0, numa_node);
if (dev->mem == NULL) {
VHOST_LOG_CONFIG(ERR,
"(%d) failed to allocate memory for dev->mem\n",
dump_guest_pages(dev);
+ if (async_notify) {
+ for (i = 0; i < dev->nr_vring; i++)
+ dev->notify_ops->vring_state_changed(dev->vid, i, 1);
+ }
+
return RTE_VHOST_MSG_RESULT_OK;
free_mem_table:
uint16_t num_queues, queue_size;
struct virtio_net *dev = *pdev;
int fd, i, j;
+ int numa_node = SOCKET_ID_ANY;
void *addr;
if (msg->size != sizeof(msg->payload.inflight)) {
return RTE_VHOST_MSG_RESULT_ERR;
}
+ /*
+ * If VQ 0 has already been allocated, try to allocate on the same
+ * NUMA node. It can be reallocated later in numa_realloc().
+ */
+ if (dev->nr_vring > 0)
+ numa_node = dev->virtqueue[0]->numa_node;
+
if (dev->inflight_info == NULL) {
- dev->inflight_info = calloc(1,
- sizeof(struct inflight_mem_info));
+ dev->inflight_info = rte_zmalloc_socket("inflight_info",
+ sizeof(struct inflight_mem_info), 0, numa_node);
if (!dev->inflight_info) {
VHOST_LOG_CONFIG(ERR,
"failed to alloc dev inflight area\n");
struct vhost_virtqueue *vq;
void *addr;
int fd, i;
+ int numa_node = SOCKET_ID_ANY;
fd = msg->fds[0];
if (msg->size != sizeof(msg->payload.inflight) || fd < 0) {
"set_inflight_fd pervq_inflight_size: %d\n",
pervq_inflight_size);
+ /*
+ * If VQ 0 has already been allocated, try to allocate on the same
+ * NUMA node. It can be reallocated later in numa_realloc().
+ */
+ if (dev->nr_vring > 0)
+ numa_node = dev->virtqueue[0]->numa_node;
+
if (!dev->inflight_info) {
- dev->inflight_info = calloc(1,
- sizeof(struct inflight_mem_info));
+ dev->inflight_info = rte_zmalloc_socket("inflight_info",
+ sizeof(struct inflight_mem_info), 0, numa_node);
if (dev->inflight_info == NULL) {
VHOST_LOG_CONFIG(ERR,
"failed to alloc dev inflight area\n");
vq->last_avail_idx += resubmit_num;
if (resubmit_num) {
- resubmit = calloc(1, sizeof(struct rte_vhost_resubmit_info));
+ resubmit = rte_zmalloc_socket("resubmit", sizeof(struct rte_vhost_resubmit_info),
+ 0, vq->numa_node);
if (!resubmit) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for resubmit info.\n");
return RTE_VHOST_MSG_RESULT_ERR;
}
- resubmit->resubmit_list = calloc(resubmit_num,
- sizeof(struct rte_vhost_resubmit_desc));
+ resubmit->resubmit_list = rte_zmalloc_socket("resubmit_list",
+ resubmit_num * sizeof(struct rte_vhost_resubmit_desc),
+ 0, vq->numa_node);
if (!resubmit->resubmit_list) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for inflight desc.\n");
- free(resubmit);
+ rte_free(resubmit);
return RTE_VHOST_MSG_RESULT_ERR;
}
}
if (resubmit_num) {
- resubmit = calloc(1, sizeof(struct rte_vhost_resubmit_info));
+ resubmit = rte_zmalloc_socket("resubmit", sizeof(struct rte_vhost_resubmit_info),
+ 0, vq->numa_node);
if (resubmit == NULL) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for resubmit info.\n");
return RTE_VHOST_MSG_RESULT_ERR;
}
- resubmit->resubmit_list = calloc(resubmit_num,
- sizeof(struct rte_vhost_resubmit_desc));
+ resubmit->resubmit_list = rte_zmalloc_socket("resubmit_list",
+ resubmit_num * sizeof(struct rte_vhost_resubmit_desc),
+ 0, vq->numa_node);
if (resubmit->resubmit_list == NULL) {
VHOST_LOG_CONFIG(ERR,
"failed to allocate memory for resubmit desc.\n");
- free(resubmit);
+ rte_free(resubmit);
return RTE_VHOST_MSG_RESULT_ERR;
}
msg->size = sizeof(msg->payload.state);
msg->fd_num = 0;
+ vhost_user_iotlb_flush_all(vq);
+
vring_invalidate(dev, vq);
return RTE_VHOST_MSG_RESULT_REPLY;
rte_free(vq->log_cache);
vq->log_cache = NULL;
vq->log_cache_nb_elem = 0;
- vq->log_cache = rte_zmalloc("vq log cache",
+ vq->log_cache = rte_malloc_socket("vq log cache",
sizeof(struct log_cache_entry) * VHOST_LOG_CACHE_NR,
- 0);
+ 0, vq->numa_node);
/*
* If log cache alloc fail, don't fail migration, but no
* caching will be done, which will impact performance
return RTE_VHOST_MSG_RESULT_ERR;
VHOST_LOG_CONFIG(DEBUG,
- ":: mac: %02x:%02x:%02x:%02x:%02x:%02x\n",
+ ":: mac: " RTE_ETHER_ADDR_PRT_FMT "\n",
mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
memcpy(dev->mac.addr_bytes, mac, 6);
break;
case VHOST_USER_SET_VRING_NUM:
case VHOST_USER_SET_VRING_BASE:
+ case VHOST_USER_GET_VRING_BASE:
case VHOST_USER_SET_VRING_ENABLE:
vring_idx = msg->payload.state.index;
break;
}
}
- if (unlock_required)
- vhost_user_unlock_all_queue_pairs(dev);
-
/* If message was not handled at this stage, treat it as an error */
if (!handled) {
VHOST_LOG_CONFIG(ERR,
}
}
+ if (unlock_required)
+ vhost_user_unlock_all_queue_pairs(dev);
if (!virtio_is_ready(dev))
goto out;